Deep Reinforcement Learning

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlooking performance-critical structural properties of programs that are essential for generating optimized code. In this work, we propose CudaPerf, a reflective RL framework that incorporates both verifiable execution rewards and structural code-aware rewards derived from parallelization features (e.g., memory coalescing, occupancy, Arithmatic Intensity, and synchronization patterns). CudaPerf operates in two stages: (1) an offline pairwise ranking module that learns to distinguish strong and weak program candidates via contrastive comparisons, and (2) an online RL training phase that jointly optimizes for correctness, performance, and structural efficiency through a unified reward signal. To further enhance learning, CudaPerf utilizes iterative refinement using execution feedback enabling progressive improvement of generated candidates. We also introduce a dataset comprising 2.9k C to CUDA and 1k PyTorch to CUDA programs, each paired with diverse input configurations and multiple CUDA implementations encompassing diverse optimization strategies. CudaPerf is evaluated across multiple benchmarks comprising both C to CUDA and PyTorch to CUDA transformations. Empirical findings suggest that CudaPerf significantly outperforms strong baselines, including Qwen-3-32B (for C to CUDA) and CUDA Agent (for PyTorch to CUDA) by achieving up to 5X & 3.32X improvements in speedup, and 17% & 7% improvements in correctness, respectively.

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle. We frame AIF as policy optimization and show that, for closed-loop control policies, EFE minimization can be formulated as a convex Markov decision process (MDP). This perspective reveals that policy-dependent reward prediction errors transmit natural gradients of the expected free energy backwards in time rather than up a hierarchy. Finally, we show that coupling world-model learning with policy optimization gives active inference the structure of performative reinforcement learning. Together this places EFE minimization within modern reinforcement learning and optimization theory and opens a route toward principled algorithms for active inference.

Large-scale online reinforcement learning (RL) is the predominant means of eliciting advanced abilities including long-term reasoning and agentic tool use in large language models (LLMs). However, continuing to scale it across vast task domains of interest remains challenging in both computational infrastructure and cost, especially when considering RL as merely a one-off learning stage. Recently, a widely used technique for distilling knowledge across various domains and training stages, multi-teacher on-policy distillation (MOPD), helps to decouple the RL stage, saving costs, while maintaining generality across vast domains. Nonetheless, similar to online RL, MOPD requires coupled inference and backward passes, which continues to limit its scalability and computational efficiency. To address these challenges, we propose REGEN: Replay-recycling for Expert-to-Generalist Distillation with Offline RL. Instead of distilling from multiple teacher models, REGEN trains a generalist by simply recycling the replay memory -- the free by-product of the teachers' specialized RL training -- and employing offline RL algorithms. REGEN completely decouples the rollout sampling from the backward training process and thus greatly reduces the training cost. Across mathematical reasoning, code generation, and instruction following, REGEN matches the accuracy of MOPD at substantially lower cost. It potentially turns online RL into a data synthesis process instead of a one-off learning stage, and can be extended to large-scale post-training without requiring heavy computational load. Code is available at https://github.com/yunjie-sysu/REGEN.

Leveraging large language models (LLMs) for molecular generation has shown remarkable potential in chemical and drug design. Current methods primarily rely on supervised training or fine-tuning with limited datasets, which are insufficient to capture complex molecular design objectives. While some approaches attempt to guide generation toward specific goals, they often lack direct optimization mechanisms, making it difficult to align generated molecules with desired properties. To tackle these challenges, we propose \textbf{LLMol}, a principled reinforcement learning framework that directly incorporates verifiable rewards for targeted molecule generation. The key insight is to formulate molecular design as a goal-conditioned sequence prediction task, where verifiable rewards serve as explicit supervision to drive generation toward desired objectives. LLMol follows a two-stage training paradigm combining supervised learning and reinforcement learning. In the first stage, large language models are supervised fine-tuned to capture chemical syntax and molecular distributions. In the second stage, we introduce Reinforcement Learning with Verifiable Rewards (RLVR), which directly integrates property-based reward signals to guide molecular generation toward task-specific objectives. To address the high variance and instability common in discrete sequence optimization, we adopt Group Relative Policy Optimization (GRPO), a stable on-policy algorithm that smooths reward signals and improves training robustness. This framework enables LLMol to effectively handle a range of molecular design tasks, including single-property targeting (e.g., penalized logP, QED) and structure-constrained optimization. Experimental results demonstrate that LLMol consistently outperforms existing methods, achieving higher success rates and improved efficiency across diverse molecular benchmarks.

Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge. As embodied agents become increasingly capable, there is a growing demand for compact models that can serve as an on-device brain, preserving the broad general intelligence of LLMs while enabling effective high-level interaction with embodied environments. Existing approaches, however, often prioritize either general-purpose intelligence or specialized embodied capabilities, making it challenging to satisfy both requirements within a single model. We present \textbf{Athena-Brain-8B}, an 8B LLM designed to serve as an on-device brain for embodied intelligence for embodied intelligence. Through a multi-stage post-training pipeline consisting of General Supervised Fine-Tuning, General Reinforcement Learning, Embodied Expert training, and Model Merge, Athena-Brain-8B maintains strong general capabilities while acquiring strong high-level embodied interaction capabilities and generating concise responses for efficient embodied interaction. Experimental results demonstrate the effectiveness of Athena across both general and embodied evaluations. Compared with the corresponding Qwen3-8B thinking model, Athena-Brain-8B achieves comparable performance on general language and reasoning benchmarks while generating substantially shorter responses. On in-domain embodied benchmarks, Athena-Brain-8B consistently outperforms models of similar scale and surpasses several substantially larger frontier models evaluated zero-shot, demonstrating that compact language models can effectively integrate strong general intelligence with embodied capabilities.

Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective. This "reward-seeking" is difficult to measure because a model that pursues the grader's judgment and one that pursues the intended objective behave identically whenever the grader rewards the intended behavior. We measure reward-seeking using Contrastive Synthetic Document Finetuning to change a model's beliefs about what the grader rewards, putting those beliefs in conflict with what users or developers want, and measuring the rate at which the model adopts each party's preferred behavior. Applied to intermediate checkpoints of a capabilities-focused OpenAI o3 RL run, without safety training, we find that these checkpoints often side with grader preferences over those of users or developers on coding and alignment tasks. This tendency to side with the grader trends upward throughout RL training. For example, in an environment that forces a choice between keeping a promise to a supervisor and breaking it to complete the task, a late capabilities-focused o3 checkpoint breaks the promise 87% of the time when SDF documents say the grader rewards task completion, versus 9% when they say it rewards honesty (a choice its chain-of-thought often makes explicit). An earlier checkpoint is far less sensitive (40% vs. 24%). Our method also generalizes to reward-hacking models. A model organism trained to reward-hack (gpt-oss-120b) is more than twice as sensitive to grader preferences as the unmodified model, with the mean behavioral shift in favor of the grader rising from 33% to 86%. These results indicate that RL can increase reward-seeking over the course of training, producing models that may act against their developers' intentions when they believe that doing so leads to higher reward.

Reinforcement learning (RL) methods for learning-to-rank (LTR) can optimize (almost) any ranking goal, e.g., from precision or discounted cumulative gain to fairness-of-exposure or ranking distillation. However, standard RL is ineffective and computationally costly due to the enormous action space in LTR settings. Existing methods reach computational efficiency through custom gradient computation algorithms, but they are very complex to implement and often clash with auto-differentiation. Consequently, existing RL for LTR is not attractive to many practitioners. We reconsider RL for LTR while actively avoiding reliance on custom gradients. Contrary to the existing approaches, we focus on variance reduction and GPU computation. In doing so, we discover that high sample-efficiency can be reached through baseline corrections and partial marginalization. Furthermore, we propose an abstraction that places gradient estimation behind a document-exposure distribution, this enables seamless plug-and-play integration with auto-differentiation. Thereby, one only has to implement a loss as a differentiable function of exposure and RL for LTR can optimize it using auto-differentiation. Our experimental results reveal that our new exposure-based RL for LTR approach converges considerably faster and at significantly higher ranking performance than existing custom gradients, with no additional costs in computation time when using GPUs. In contrast, existing custom gradients result in severe stability issues when converging over many epochs, which never occur for our methods. Thus, we considerably improve RL for LTR methodology by increasing its effectiveness, efficiency, and ease of application.

The deployment of high-speed Uncrewed Aerial Vehicles (UAVs) in 3D aerial highways necessitates robust coordination of physical flight kinematics and multi-tier network handovers. While Deep Reinforcement Learning (DRL) offers rapid tactical control, it lacks the zero-shot strategic reasoning required to quickly adapt to dynamic Integrated Terrestrial and Non-Terrestrial Networks (ITNTNs). Conversely, Large Language Models (LLMs) excel at semantic reasoning but suffer from high inference latency, rendering them unsuitable for real-time aerodynamic control. To bridge this gap, we propose a novel Hierarchical LLM-driven control framework. A massive cloud-based LLM deployed on a High-Altitude Platform Station (HAPS) manages slow-timescale global load balancing, while lightweight edge-LLMs on individual UAVs translate local observations into tactical sub-goals. These sub-goals guide a fast-timescale physical DRL controller to execute collision-free, handover-aware trajectories. Simulation results demonstrate that our agentic architecture significantly reduces collision rates and improves aggregate system throughput compared to existing baselines.

The increasing complexity of mobile networks necessitates intelligent and dynamic control strategies for efficient, energy-conserving management. We propose a world model-based approach for network control that enables adaptive configuration of crucial parameters. The world model is trained from historical data and predicts the impact of its actions on future network states. Our controller leverages the model's uncertainty estimate to robustly find optimal network configuration changes. Furthermore, the optimization objective can be changed dynamically without model retraining. We demonstrate the effectiveness of the approach in simulated closed-loop control of a mobile network energy-saving feature. Our results show improved performance in balancing energy savings with quality of service, compared to traditional methods and reinforcement learning approaches. Finally, we show the world model performance on real network data from, and evaluate counterfactual actions proposed by the controller under various throughput constraints.

Transfer-oriented reinforcement learning requires evaluating algorithms along dimensions that go beyond standard sample efficiency. We focus on two dimensions: practical efficiency, which asks whether conclusions about algorithm suitability change under wall-clock rather than interaction-based budgets, and robustness under dynamics mismatch, which asks how different learning paradigms respond to variability in the training distribution induced by domain randomization. We provide two insights to reinforcement-learning practitioners. First, comparing the sample efficiency of different algorithms is often an insufficient criterion in transfer-oriented settings. The wall-clock time required to train a decent policy is an important consideration for practitioners, and we find that the sample-inefficient PPO algorithm can produce a performant policy faster than relatively more sample-efficient algorithms such as SAC and TD-MPC2, validating the common understanding of massively parallel training paradigms. Second, domain randomization can help different kinds of algorithms learn robust policies. In particular, although PPO, SAC, and TD-MPC2 represent different RL paradigms - on-policy, off-policy, and model-based learning and planning, respectively - we find that domain randomization affects all three algorithms in a similar way. To the best of our knowledge, this is the first controlled comparison of the effect of domain-randomization coverage on PPO, SAC, and TD-MPC2 under the same transfer protocol. Taken together, these two insights highlight the importance of evaluating RL algorithms not only by sample efficiency, but also by practical considerations such as training time and the algorithms' ability to produce usable policies.

Long-horizon rollout generation has become the dominant systems bottleneck in agentic reinforcement learning (RL). As agents interact with environments over many turns, trajectories rapidly grow to tens of thousands of tokens, making synchronous RL training increasingly constrained by rollout. We propose WAR, a workload-aware rollout system that substantially accelerates synchronous agentic RL by jointly optimizing decoding and scheduling. WAR is built on a key observation: the optimal rollout optimization strategy depends on runtime load: (1) Under low load, WAR enables model-free speculative decoding with SuffixDecoding, which reuses suffix patterns from previously completed trajectories as speculative drafts for future rollouts. Unlike model-based drafters, SuffixDecoding introduces no additional draft model and avoids GPU contention with rollout generation. (2) Under high load, where saturated batched decoding leaves limited room for speculative speedup, WAR shifts the optimization focus to cache-aware scheduling. A global scheduler places requests across rollout replicas based on cache locality, trajectory progress and server load, reducing redundant KV-cache recomputation and mitigating load imbalance. By combining decoding-level suffix reuse with system-level rollout scheduling, WAR delivers robust throughput improvements across workload regimes without changing the underlying RL algorithm. WAR improves long-context agentic rollout throughput by 1.4x under low load and up to 1.6x under high load. These results show that WAR removes a major rollout bottleneck in synchronous agentic RL and provides a practical path toward scalable long-context agent training.

The Credit Assignment Problem (CAP) is fundamental to developing efficient and explainable Reinforcement Learning (RL) agents. Existing frameworks, whether relying on temporal contiguity or hindsight-conditioned reward reweighting, frequently fail to attribute properly between an agent's policy (skill) and environmental stochasticity (luck). A principled approach to CAP must isolate the true causal drivers of observed outcomes from spurious correlations and environmental randomness. We introduce Counterfactual Shapley Credit Assignment, a novel framework grounded in causal theory that attributes credit and blame via the Counterfactual Shapley Value ($φ$-value). By redistributing environmental rewards, $φ$-values enhance temporal credit assignment across three critical dimensions: sparse causality, high stochasticity, and delayed rewards, all while preserving the optimal policy. We derive a consistent estimator that computes $φ$-values efficiently, enabling a new class of policy gradient methods, $φ$-PPO, combined with Prioritized Trajectory Replay (PTR). Empirical results demonstrate that $φ$-values align precisely to the ground truth causes of task rewards with superior sample efficiency in challenging environments where prior state-of-the-art methods fail to converge.

We introduce the vehicle routing problem with stochastic demands and outsourcing options (VRP-SDO), in which a logistics service provider partitions customer requests into customers outsourced to a common carrier and customers committed to its fixed fleet. The latter induces a vehicle routing problem with stochastic demands (VRP-SD), solved dynamically. Demands are revealed upon visit; residual demand may be served by other vehicles or after restocking at the depot. Work beyond the regular shift incurs overtime costs, and the unit outsourcing cost decreases with the expected outsourced demand. The objective is to minimize expected travel, overtime, and outsourcing costs. We propose an iterative two-level methodology whose first level partitions customers into committed and outsourced subsets, while the second level estimates the expected VRP-SD routing cost. To avoid solving this problem from scratch at every iteration, we learn an offline routing policy that estimates costs almost instantly for any committed subset. An iterated local search establishes the first-level partitions. We formulate the second level as a Markov decision process and solve it with a deep Q-network whose state is represented by a graph attention network aggregating customer and vehicle information by relevance to the acting vehicle. Trained offline on instances with variable customer cardinality and locations, the policy applies to any daily customer realization; online fine-tuning improves the cost approximation. Experiments show that our policy reduces routing costs by 19.6% relative to a state-of-the-art method and by at least 29.6% over classical heuristics. Our overall algorithm saves 13.7% on average over the version without the attention-based representation and generates high-quality decisions within minutes, whereas benchmarks without an offline-trained estimator require over an hour.

In recent years, large-scale vision-language models have been driving a paradigm shift in intelligent remote sensing image interpretation. By incorporating textual semantic information, the cognitive expression, semantic understanding, and human-computer interaction capabilities of interpretation models have been significantly improved, achieving initial progress in the field of Synthetic Aperture Radar (SAR) image interpretation. However, SAR images are affected by factors such as coherent imaging mechanisms, complex scattering characteristics, speckle noise interference, and target-background coupling, resulting in complex and variable image features with significant uncertainties and specializations. Existing SAR vision-language models do not yet possess the step-by-step analysis, logical judgment, and self-correction capabilities of human experts, making it difficult to support reliable intelligent interpretation in complex scenarios. To address this issue, this paper proposes a large-scale reasoning model, FUSAR-R1, for intelligent interpretation of SAR images. The model first constructs explicit chain-of-thought reasoning data by simulating the interpretation process of human experts and uses this data to guide instruction learning, thereby endowing the model with basic reasoning capabilities. Subsequently, a reinforcement learning strategy is introduced to optimize the model's outputs based on inference results, enabling self-correction and more reliable reasoning. Experimental results demonstrate that FUSAR-R1 consistently outperforms existing multimodal large-scale models across various SAR interpretation tasks, including target detection, target counting and classification, and land-cover category recognition.

Safe model-based reinforcement learning (RL) often bridges control-theoretic analysis and RL for robots to safely explore (partially) unknown system dynamics while deriving control actions for task efficiency. The control performance and safety assurance typically rely on prior knowledge of partially modeled nominal system dynamics and the data-driven models that compensate for residual model uncertainties. However, existing methods often overlook the structure of residual model uncertainties (e.g., components affine in control), which could lead to overly conservative robot behaviors or invalid safety guarantees under the safe learning-based controllers. This paper proposes a safe reinforcement learning framework that learns control-affine dynamics with a certifiable data-driven safe policy using control barrier functions (CBF). Specifically, we first use Control-Affine Random Fourier Features (ARFF) to model robot dynamics in a control-affine form, which offers computational efficiency that scales with dataset size and reduces potential model bias for model-based reinforcement learning. Then, a model-free, efficient uncertainty quantification method using adaptive conformal prediction (ACP) is applied to quantify the uncertainty in the safety constraint arising from the learned control-affine dynamics. This allows for data-driven safety assurance amenable to principled and efficient controller synthesis with CBF. Simulation results on the cartpole and the 3D quadrotor platforms demonstrate the effectiveness of the proposed framework.

Experiment trackers show how training is progressing, but changing a live run still usually requires trainer-specific code. We present Interactive Training 2, an open-source control plane for steering training through a shared protocol. Training applications declare which settings and actions they expose, humans and automated controllers submit requests through the same interface, and the training loop validates and applies them at safe control points. A customized Aim workspace combines live metrics and controls with a chronological record of requests and outcomes. We demonstrate the system across five NLP and reinforcement-learning workflows. The released code and traces provide a reusable foundation for auditable human- and agent-guided training.

This paper presents our system for Task 3 of the CLEF 2026 FinMMEval Lab, which requires daily long, flat, or short trading decisions for Bitcoin (BTC) and Tesla (TSLA) using news and historical market data. We formulate the problem as a discrete-action Markov Decision Process and compare four deep reinforcement learning algorithms: Policy Gradient (PG), Proximal Policy Optimization (PPO), Deep Q-Learning (DQL), and Deep Deterministic Policy Gradient (DDPG). The agents use technical indicators, cyclical calendar encodings, and daily news sentiment scores produced by LLaMA 3.2 1B. To reduce overfitting and align training with the objective of outperforming buy-and-hold, we introduce an alpha reward based on excess market return and randomize episode start dates. Hyperparameters are optimized with Ray Tune over 180 trials per algorithm-asset pair, with early stopping and model selection based on validation Sharpe ratio. On the CLEF Task 3 test set, DDPG achieves the strongest overall performance. DQL was selected a priori for the live endpoint because it obtained the highest validation Sharpe ratio, with selection performed without access to the test period. For TSLA, DDPG and DQL achieve cumulative returns of 54.96% and 52.62%, respectively, compared with 16.45% for buy-and-hold. For BTC, DDPG achieves a positive return of 1.58% while buy-and-hold declines by -34.27%. The results also reveal a substantial validation-to-test generalization gap, highlighting the difficulty of transferring policies selected in bull-market conditions to a bear-market regime.

Increases in photovoltaic generation, charging of electric vehicles and heat-pump demand challenge operating limits in low-voltage distribution grids. This requires curative curtailment methods that can operate under sparse observability, noisy measurements, and imperfect grid models. Unlike prior end-to-end reinforcement-learning approaches for partially observable curtailment, this work decouples congestion detection and control by combining a random-forest violation pre-classifier with an actor-critic controller, and evaluates its robustness to measurement noise and grid-parameter mismatch. The framework is tested on a real low-voltage grid using synthetic future operating scenarios with low observability and controllability. With accurate grid parameters, the controller reduces total violation magnitude by 98.9%, and this performance remains nearly unchanged under the tested measurement-noise settings. Grid-model mismatch proves to be more challenging, but the controller still mitigates most violations under the tested mismatch assumptions.

Learned policies trained end-to-end on large datasets often remain brittle in high-precision tasks and struggle with generalization. We find that these limitations largely stem from a lack of structure and focus in data collection. Our key insight is to leverage dense data collection only for the critical segment of contact-rich tasks and to rely on traditional planning during simple free-space motion. We propose an automated data-collection scheme in combination with offline deep reinforcement learning for the critical segment of the task, eliminating reliance on a teleoperator's skill and on online policy updates. Across four challenging real-world tasks, using only 2 to 2.5 hours of autonomous data collection, we achieve an average success rate of 96%, compared to the strongest baseline at 55%. Notably, performance remains high in out-of-distribution scenarios where end-to-end approaches struggle. Our results pave the way for targeted data collection for contact-rich tasks and for high success rates in precision applications.

Deep reinforcement learning (DRL) has a longstanding tradition in addressing the reach-avoid task problem, especially for controlling robotic arms. While this task serves as a baseline environment within the research community, the ability of DRL to effectively learn the each-avoid task in complex and realistic scenarios beyond simplified and restricted tabletop settings remains uncertain. In this paper, we present, for the first time, a comprehensive benchmark for the reachavoid task that accurately captures real-world complexities without simplifications. We demonstrate a diverse range of settings for robotic arm reach-avoid task, which can be used for evaluating DRL research. We achieved this by utilizing the MuJoCo MJX physics engine and parallelizing both the simulation environment and DRL algorithms using the Brax library. We achieved state-of-the-art results with success rates of 96.1% (UR5e) and 98.8% (Franka Emika Robot) for the reach task and 86.8% (UR5e) and 95.2% (Franka) for the static reachavoid task. Our results indicate that while in previous works DRL agents could solve, for example, a reach task in a simplified setting perfectly, their agents performance collapses when evaluated in realistic scenarios. Overall, this work identifies that additional research is still required to claim the successful resolution of the robotic arm reach-avoid task using DRL. The environment and benchmarking code is available as open source at the following link

Rollout generation is a major bottleneck in Reinforcement Learning (RL) for Mixture-of-Experts (MoE) Large Language Models, motivating low-precision rollout acceleration such as FP8. As an emerging low-precision format, NVFP4 combines fine-grained scaling for accuracy preservation with native W4A4 FP4 GEMMs for higher throughput than FP8. However, we find that directly applying NVFP4 to MoE RL rollout is impractical. NVFP4 rollout with BF16 training collapses after roughly 150 steps, accompanied by rapidly growing rollout-trainer log-probability gaps. Through training-inference error analysis and controlled ablations, we identify activation error, rather than weight error, as the dominant source of FP4 RL instability: weights can be synchronized and aligned by a shared quantization-dequantization path, whereas activations are recomputed online and error is amplified by the coarse E2M1 grid. Therefore, to stabilize NVFP4 RL for MoE, we propose QUantization-error Alignment across Dual Sides (QUADS). On the trainer side, we introduce Asymmetric Quantization-Aware Training fake-quantizing weights while keeping activations unquantized for better alignment. On the rollout side, Residual Activation Compensation corrects high-error activation channels while preserving native W4A4 GEMMs. In our MoE RL experiments on several benchmarks, QUADS achieves BF16-level accuracy, improves average pass@1 by 21.49 points over naive NVFP4 RL, and delivers ~16% higher rollout throughput than FP8.

End-to-end deep reinforcement learning (DRL) for zero-shot object-goal visual navigation remains challenged by the sim-to-real gap, particularly variations in object appearance and restricted camera field-of-view (FoV). This letter proposes a Temporal Difference-Relational Network (T-DRN) for robust zero-shot sim-to-real transfer. T-DRN combines a Siamese difference-based feature extractor, which computes relational difference between the target and observed objects to produce domain-independent representations, with a dual-frame temporal buffer that preserves short-term object continuity under narrow FoV. Extensive experiments in AI2-THOR demonstrate that T-DRN improves zero-shot generalization in terms of success rates over strong baselines. Furthermore, T-DRN is systematically validated on a physical wheeled robot, demonstrating robust performance under real sensing and actuation constraints and supporting the feasibility of direct sim-to-real transfer.

Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. This limits diversity and, for person-centric prompts, can reflect or amplify demographic skew. We formalize this problem as target-mode coverage, the coverage of a predefined set of semantically specified modes, and propose multi-axis max@K, a group-based reinforcement learning objective for improving it in diffusion-based T2I models. Given a group of samples and one score per target mode, multi-axis max@K first takes the maximum score across samples for each mode and then sums these per-mode maxima. The resulting credit assignment gives a sample positive weight on a mode only when it raises that mode's group maximum, so different samples can contribute to different modes. We validate the credit-assignment mechanism on a synthetic mixture and on SD3.5-M with deterministic pixel-based color rewards, and then apply the same objective to perceived-appearance fairness. On held-out prompts, multi-axis max@K improves the Fairness Score by 0.23-0.36 over the base model under three automatic evaluators, while maintaining image quality and text alignment. Code is available at https://github.com/KuOnoda/multi-axis-maxk.

A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256K tokens or below and rely on length generalization at deployment. The gap is especially important for AI agents, whose observations, tool outputs, documents, and prior decisions accumulate over long trajectories. LongStraw is an architecture-aware execution stack for million-token RL post-training under a fixed GPU budget, instantiated with Group Relative Policy Optimization (GRPO). It evaluates the shared prompt without autograd, retains only model-specific state needed by later tokens, and replays short response branches one at a time, reducing the live training graph at the cost of additional replay time. We implement it for the hybrid recurrent and full-attention Qwen3.6-27B and the compressed-attention mixture-of-experts GLM-5.2. On eight H20 GPUs, LongStraw completes grouped Qwen scoring and response backward at 2.1M positions for groups of 2 and 8; increasing the group size adds only 0.21 GB of peak allocated memory, while a separate stress test reaches 4.46M positions. On 32 H20 GPUs, we validate the end-to-end LongStraw execution path for a 2.1M-token prompt across all 78 layers of GLM-5.2. These experiments establish execution capacity rather than complete training correctness because the captured prompt state is detached and some distributed forward and gradient composition paths remain incomplete.

Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions, leaving a supervision gap between episode-level outcomes and token-level policy learning. We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills and distills their behavioral effect back into the policy model. SEED first fine-tunes the policy to analyze completed trajectories and generate natural-language skills that capture reusable workflows, decisive observations, or failure-avoidance rules. During RL, the current policy both collects trajectories and serves as the analyzer that extracts hindsight skills from them. Policy updates therefore improve subsequent decision making and skill analysis together, allowing hindsight supervision to evolve with the policy. SEED then re-scores the sampled actions under ordinary and skill-augmented contexts, converting the skill-induced probability shift into a dense token-level on-policy distillation signal. This signal is jointly optimized with outcome-based RL, keeping the auxiliary supervision aligned with the current trajectory distribution. Extensive experiments on text-based and vision-based agentic tasks show that SEED consistently improves performance and sample efficiency, exhibiting robust generalization to unseen scenarios. Our code is available at https://github.com/jinyangwu/SEED.

3D geometric tooth alignment planning, which determines sequential trajectories from initial malocclusion to the final target alignment, is a cornerstone of modern digital orthodontics. This paper presents a novel deep reinforcement learning (DRL) framework to automate the generation of these alignment paths. We formulate the planning process as a Markov Decision Process (MDP) to capture its sequential decision-making nature, focusing on optimizing geometric trajectories while integrating essential spatial constraints, such as inter-dental collision avoidance and path efficiency. The proposed method leverages the Deep Deterministic Policy Gradient (DDPG) algorithm, enhanced by three key innovations: (1) a Transformer-based agent to model complex spatial interactions between teeth and manage high-dimensional state-action spaces; (2) a dynamic masking scheme that restricts movement to a sparse subset of teeth per step, better reflecting the clinical logic of sequential alignment; and (3) a two-stage curriculum learning strategy that gradually increases task difficulty to ensure training stability and efficient path discovery. We evaluate our approach on a dataset of 10K expert-designed treatment plans based on clinical data. Experimental results demonstrate that our method outperforms existing baselines in terms of path safety and geometric efficiency, providing a robust and automated solution for 3D geometric orthodontic alignment planning.

We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization problems and derive the corresponding policy gradient methods, leading to continuous-time variants of proximal policy optimization (PPO) and group relative policy optimization (GRPO). As a primary application, we develop a complete continuous-time RL framework for fine-tuning score-based discrete diffusion models. The proposed framework enables reward-driven optimization without requiring differentiability on the reward signals. In contrast to the existing GRPO-based approaches that only rely on terminal rewards, our formulation allows intermediate reward or advantage signals to be incorporated throughout the denoising trajectory. Importantly, when specialized to masked diffusion models (MDMs), our framework encompasses a rich class of policy parameterizations over the vocabulary simplex with analytically tractable probability ratios, providing a unified perspective on exploration and policy optimization in MDMs. For masked diffusion large language models (dLLMs), we further propose trajectory subsampling techniques to efficiently estimate computationally prohibitive trajectory likelihoods, reducing the computational cost of computing per-position probability ratios. We showcase the effectiveness of our methods on both low-dimensional entropy-regularized optimization problems and RL post-training of dLLMs on mathematical reasoning and coding tasks.

In this paper, we introduce Lighthouse RL, a sample-efficient reinforcement learning (RL) approach for analog circuit sizing. Traditional methods lack generalization across different performance targets, while standard RL approaches waste resources exploring unpromising regions. Our method addresses these inefficiencies through a strategic reset strategy that initializes episodes from high-performing configurations discovered during training, called "lighthouses". These states, which are closer to the target objectives, guide exploration toward promising regions. When compared to RL and Bayesian optimization methods from the literature, we demonstrate the effectiveness of our approach on a 2D benchmark problem and on two analog circuits, showing significant improvements in sample efficiency (up to 1.72x faster), optimization performance (100% vs. 0-87% success rate), generalization (75% vs. 0-50% extrapolation success), and objective maximization. This efficiency is particularly valuable for computationally expensive black-box optimization problems, and our reset strategy can be used as a plug-and-play enhancement for any RL-based optimization approach.

We suggest using the Lyapunov characteristic exponent (LCE) as a dense reward signal for the reinforcement learning problem of stabilizing the inverted pendulum with vertical motion. With LCE, the agent not only successfully found the oscillatory motion known as the Kapitza pendulum but also damped the pendulum's pivoting, leaving it in a strictly upright position.

Explainable Reinforcement Learning (XRL) seeks to make Reinforcement Learning (RL) policies more transparent and interpretable, a key requirement in safety-critical and human-centric scenarios. However, it is mostly based on user studies, thus targeting the needs of a specific audience and lacking shared evaluation metrics. On the other hand, logic-based approaches within eXplainable Artificial Intelligence (XAI) provide compact, human-readable abstractions of decision-making. However, the systematic quantification of the explainability degree of logical representations remains an open problem. This work aims to advance the state of the art in XRL by introducing objective and planning-oriented metrics for policy explainability in RL settings. At the same time, it contributes to the field of logic for XAI by providing a principled way to quantify the explainability of logical rules, moving beyond common-sense assessments and simple propositional fragments. We employ Inductive Logic Programming (ILP) to extract symbolic representations of RL policies and define a novel set of explainability metrics, including activation rate, feature coverage, syntactic distance and semantic distance. These metrics quantify alignment between symbolic rules and agent behavior, the role of features in decision-making, and the evolution of policies during training and across agents in single and multi-agent RL. Experiments across different RL domains show that the proposed metrics highlight action-specific learning dynamics beyond global return, provide fine-grained insights into domain features beyond classical approaches for global feature importance estimation, and uncover coordination, specialization, and adaptation patterns in MARL. Moreover, they provide crucial insights for the transfer and generalization of action-specific policies.

Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes. State-of-the-art algorithms such as PPO, RLOO, and GRPO inherit their rollout topology from RLHF: for each prompt, N independent trajectories are sampled from the initial state, and an advantage is computed by subtracting a group baseline. This design ignores a defining property of agent sandboxes. They are deterministic, snapshottable, and resumable from any intermediate state. We argue that this property enables a fundamentally different rollout topology: rather than N independent trees of depth T, one can construct a single tree of N leaves whose siblings share prefixes, and therefore share variance. We instantiate this idea as Branching Policy Optimization (BPO), a sandbox-native RL algorithm that (i) adaptively snapshots the sandbox at high-entropy decision points along a backbone trajectory, (ii) forks K alternative actions per branch point and rolls out each to termination, and (iii) computes per-step advantages from sibling returns rather than from independent prompts. We prove this estimator is unbiased and has strictly lower variance than the trajectory-level baseline, with the reduction equal to the prefix-explained portion of return variance. On WebShop, ALFWorld, and SWE-bench Verified with Qwen2.5-7B and Llama-3.1-8B backbones, BPO improves success by 3.6--6.1 absolute points over GRPO and RLOO at matched compute, halves gradient-norm variance, and matches the best baseline using 38% fewer policy updates.

Interactive driving, wherein an intelligent lead vehicle equipped with real-time traffic data coordinates route choices of connected vehicles, offers a promising approach to dynamic traffic management. To address the challenge of harmonising decisions, this paper considers the strategic information revealing framework of Bayesian persuasion. Here, the principal (lead vehicle) aims to guide the agent's (connected vehicle) partially observable sequential decision making towards its own objectives by selectively revealing information, such as real-time traffic ahead, using signals. However, the agent's farsighted response to maximize its long-term reward, renders the principal's signaling strategy design computationally challenging. We propose an online structured reinforcement learning framework to synthesize computationally efficient signaling strategy which is persuasive for a far-sighted agent. The main contributions of the paper are as follows: (i) For a monotonic agent with approximate best response, we propose MAPL, a structured policy learning algorithm for faster online learning, (ii) Identification of sufficient conditions for the supermodular structure of the Q function of the principal for a monotonic agent, (iii) Identification of sufficient conditions to ensure the persuasiveness of the principal's signaling strategy, (iv) Supermodular Q learning for Principal (SQP), which leverages the supermodular structure of principal's action value to synthesize computationally efficient signaling strategy that is persuasive for a monotonic learning agent, (v) Numerical analysis considering a real-time application of Bayesian persuasive driving for lane selection demonstrates that the proposed method is 30% cost efficient for optimising travelling rewards of both the lead and connected vehicle compared to the existing methodologies for signaling strategy design.

Generative Flow Networks (GFlowNets) offer a promising alternative to reward-maximizing reinforcement learning (RL) for large reasoning models, encouraging diverse reasoning paths by matching reward distributions rather than collapsing to dominant modes. Recent work shows promise on math and code, but scaling GFlowNet-style RL to modern post-training pipelines remains difficult: as model size, rollout horizon, reward noise, and distributed-systems complexity grow together, a learned prompt-conditional partition function becomes a source of gradient instability and engineering overhead rather than a useful normalizer. Through systematic analysis, we find that the learned partition function, previously treated as essential, can be replaced by an in-batch Monte Carlo estimate computed from the rollout group already required for training. We propose GFlowRL, a streamlined GFlowNet-style RL algorithm that removes the auxiliary partition network entirely while preserving the reward-distribution-matching objective, completed by two stabilizers: importance-sampling correction for rollout/trainer drift and asymmetric flow-gap clipping for outlier residuals. GFlowRL exceeds all counterparts on math, code, and adversarial red-teaming benchmarks, reaching a Codeforces rating of 2048 at the 14B scale (within 25 Elo of o3-mini) and attaining the highest average ASR@1 on AdvBench and HarmBench, outperforming the previous SOTA multi-turn attacker in a regime where FlowRL, a prior GFlowNet-style method, diverges. The same recipe transfers to all evaluated MoE configurations up to 235B parameters, where FlowRL again fails to converge. To our knowledge, GFlowRL is the first GFlowNet-style RL algorithm to scale stably across both dense and sparse architectures. Code will be at: https://github.com/microsoft/gflowrl

Safe reinforcement learning typically enforces safety by bounding expected cumulative costs, a criterion that often fails to detect rare but catastrophic tail events. To overcome these limitations, this paper introduces SteinGate, a boundary-aware distributional safety certificate that replaces fragile tail fitting with a robust consistency check using Kernelized Stein Discrepancy while accounting for boundary atoms induced by clipped costs. SteinGate evaluates whether observed policy rollout costs remain consistent with a safe reference distribution, providing a non-parametric safety certificate. This certificate is used to dynamically adapt the learning regime: favoring reward-improving policy updates when rollouts remain consistent with the safe reference and switching to recovery behavior when the cost tail deviates. Experiments on continuous-control benchmarks demonstrate that SteinGate significantly reduces both the frequency and severity of constraint violations during training while maintaining competitive returns relative to state-of-the-art baselines.

Reliable reinforcement learning (RL) agents must maintain operational integrity amidst sensor malfunctions, dynamic disturbances, and slow environmental shifts. The detection of out-of-distribution conditions is pivotal to determining when an agent's observations, transitions, or trajectory dynamics deviate from the assumptions underpinning its policy training. Current out-of-distribution (OOD) detection benchmarks typically evaluate image classifiers or static low-dimensional datasets, failing to account for the complex, action-dependent temporal structure inherent in RL trajectories. To address this gap, we present OOD-RL-Bench, a comprehensive and extensible framework designed to evaluate OOD detectors against categories of anomalies injected into RL trajectories. Detectors and anomaly injectors are integrated through shared interfaces and configuration, which allows new scoring methods and perturbation families to be evaluated without modification of the core benchmark loop. We evaluate the utility of the framework using a Deep Q-Network policy within the LunarLander-v3 environment. We assess the performance of each detector across a suite of anomaly types using matched-time AUROC, matched-time AUPRC, matched-time false-positive rate, detection delay, and segmented-onset metrics. Our analysis reveals significant performance variance across anomaly types: observation perturbations and regime switches are identified with high accuracy by several methods, while observation delay and action-conditioned dynamics remain difficult even when post-onset anomaly scores are compared against clean scores from the same timesteps. We make the framework, trained policy checkpoint, and complete results publicly available as a reproducible artefact.

Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them. But how does this recipe transfer to dexterous manipulation? The answer is not obvious, as manipulation involves complex, contact-rich dynamics and requires delicate regulation of contact modes and forces. We present REGRIND, a minimalist retargeting-guided RL pipeline that learns dexterous manipulation policies from a single human demonstration. REGRIND retargets human hand-object motion to a robot reference that preserves hand-object spatial and contact relationships, trains a residual RL policy in simulation to track object-centric keypoints along that reference, and transfers the resulting policy zero-shot to hardware with careful system identification. The resulting policies produce fluid, human-like behavior on two different multi-fingered hands across contact-rich tool-use tasks, including operating a pair of scissors and turning a screwdriver. Through systematic hardware experiments, we identify and analyze the key factors that govern sim-to-real transfer in dexterous manipulation, offering practical guidance for retargeting-based learning in contact-rich settings. Videos and code are available at https://yunhaifeng.com/REGRIND.

Prefabricated prefinished volumetric construction moves most building work into module factories, whose production floor operates as a flexible job shop. A major complication is decisive: long post-operation time-lags caused by concrete curing, watertightness ponding tests, and paint drying, during which a module is blocked while its workstation stays free. On benchmark instances grounded in an official national prefabrication guidebook, these lags inflate even the optimal reference makespan by about 67% on average, and ignoring them at decision time, then repairing to feasibility, is worse than every dispatching rule. We adapt a state-of-the-art dual-attention deep reinforcement learning solver through three minimally invasive, individually ablatable extensions: lag-aware dynamics with an admissible reward bound, two anticipatory lag feature channels, and liveness-masked operation- and station-type embeddings. With every extension disabled the implementation reproduces the original solver exactly, so all gains are attributable to the adaptations. We release a public, guidebook-grounded benchmark generator. On held-out instances the learned policy is the strongest solver-free scheduler: it reaches within about 4% of a constraint-programming reference and beats every dispatching rule and a genetic-algorithm metaheuristic, with its advantage widening under capacity contention, and a single size-mixed policy carries this lead across the trained range of factory sizes. It needs no solver, model, or license in the loop and re-plans within seconds of a disruption; where an exact solver can be deployed, that solver remains the quality ceiling, a boundary we map explicitly.

Active flow control involves nonlinear dynamics, partial observations, and computationally expensive simulations, making controller design particularly challenging. Deep reinforcement learning (DRL) has emerged as a powerful framework for such problems, but its success typically relies on large numbers of simulator interactions and produces neural-network policies whose decision process often remains difficult to interpret. In this work, we investigate a different paradigm: instead of optimizing neural-network parameters, we use modern coding agents to search directly for explicit executable feedback laws. We introduce a constrained heuristic-learning protocol in which an agent iteratively proposes, evaluates, and revises controller implementations while interacting exclusively through the public benchmark interface. The proposed framework is evaluated on 13 active flow-control benchmarks spanning one, two, and three-dimensional problems and compared against the strongest available DRL baselines under identical simulation budgets. The discovered heuristic controllers match or outperform the best DRL policy in 10 of the 13 environments while remaining compact, interpretable, and directly inspectable. Beyond aggregate performance, the resulting controllers reveal physically meaningful feedback mechanisms, transfer successfully across more challenging configurations, and remain competitive under varying Reynolds and Rayleigh numbers, actuator counts, and observation sparsity. These results suggest that heuristic learning through coding agents constitutes a credible and complementary alternative to conventional reinforcement learning, combining competitive performance with physically interpretable controller representations. Prompts and source code are available at https://github.com/DonsetPG/fluid-heuristic-learning.

Computer use agents (CUAs) are emerging as a powerful interface for automating complex digital workflows through visual perception and GUI execution. Online reinforcement learning with verifiable rewards (RLVR) has emerged as a key direction for scaling their capabilities. However, this paradigm is bottlenecked by verifiable data scarcity and online RL inefficiency. To break these barriers, we introduce ScaleCUA, a unified framework that scales online RL for CUAs via verifiable task synthesis and efficient training. At the data level, we design VeriGen, an end-to-end framework for generating verifiable RL tasks through iterative docker interactions and a multi-agent feedback loop. Scaled to 100+ concurrent agent workers via a shared docker interaction probe, this pipeline produces 24K+ verifiable tasks and nearly 3K high-quality RL tasks. To maximize sample efficiency, we propose Frontier Sampling, which tracks per-task capability and allocates rollouts to the current learning frontier. On the training side, we further design Visual Context Segmentation, a sliding window over recent visual context that balances rollout and training-engine pressure, yielding a 2.83x training speedup over step-wise decomposition. Together, ScaleCUA achieves 68.7% on OSWorld and 54.0% on ScienceBoard, establishing new state-of-the-art performance among open-source computer use agents. Code, models, and datasets are available at https://github.com/THUDM/SCALE-CUA.

Reinforcement learning is usually introduced through the Bellman update, yet the equation often remains abstract to undergraduates: they watch policy arrows converge but rarely observe how each value is computed or why an action is chosen. We present Q-Learning Lab, a single-file, browser-based, bilingual (Thai/English) tool for teaching tabular Q-learning that requires no installation. Beyond the usual gridworld visualization - color-coded Q-values and policy arrows on a $5 \times 5$ world - the tool exposes a live Bellman-substitution panel showing the numeric update at every step, and logs each transition, including the full pre-action Q-row, the greedy-versus-random decision under $\varepsilon$-greedy exploration, and wall-collision events, into an exportable trace. The central contribution is a learn-export-analyze loop: learners run their own agent, export the complete trace as CSV, and analyze it themselves, producing learning curves, value heatmaps, and visitation maps, turning a passive demonstration into a source of learner-generated data for reflective inquiry. We validate the tool without human-subject data through three complementary evaluations: (i) correctness of the learned values and policy against a value-iteration ground truth on the identical MDP; (ii) hyperparameter sweeps over $α$, $γ$, and $\varepsilon$ showing that every pedagogical claim the tool makes is reproducible; and (iii) a reward-editing study that uses the ground-truth optimal policy to separate two behaviorally identical but diagnostically opposite failure modes - an exploration failure versus genuine reward misspecification - that a single edited reward can produce. We also compare the tool against existing gridworld visualizers, describe its grounding in learning-by-doing pedagogy, and include a 50-minute lesson plan. The tool and all experiment code are openly available.

Greenhouse reinforcement learning can test climate-control ideas at a speed and scale that is difficult to achieve with crop experiments alone. For smart-greenhouse control, however, a single simulator return is not enough: a grower or control engineer also needs to know when the policy heats, enriches CO2, vents, manages humidity, deploys screens, or uses lamps.We propose a reproducible calibration-first reward audit framework that keeps named greenhouse-control reward components comparable across simulator training, facility-adapted rollouts, logged Autonomous Greenhouse Challenge records, and actuator-rule distillation. In GreenLight-Gym, the framework decomposes the scalar reward into conditional temperature, CO2, humidity and vapor-pressure-deficit, screen, and actuation-proxy terms; adapts GreenLight to the second Autonomous Greenhouse Challenge logged climate traces; and scores the same components on logged greenhouse data.

Multimodal BrowseComp tasks require agents to combine perception, tool use, and long-horizon reasoning over dynamic web content, challenging their ability to handle compositional structure, open-world uncertainty, and multimodal integration across extended interactions. Crucially, real-world multimodal browsing involves three distinct information-flow patterns: text-only, image-to-text, and text-to-image, yet existing data construction methods cover only the text-only and image-to-text patterns, leaving text-to-image largely unaddressed and limiting agent generality and robustness. We introduce UNIBROWSE, a unified data pipeline that for the first time simultaneously generates training data covering all three patterns, augments curated knowledge graphs with live web retrieval for improved fidelity, and introduces a novel metric of exploration degree to filter low-signal instances for efficient reinforcement learning. Through this pipeline, we produce high-quality cold-start tool-use trajectories and exploration-rich QA pairs, and train a 35B-scale agent via supervised fine-tuning and exploration-aware RL.The resulting UNIBROWSE agent achieves state-of-the-art performance on multimodal BrowseComp benchmarks, attaining an average accuracy of 54.4 across five diverse benchmarks -- an improvement of 10.5 points over its base model Qwen3.5-35B-A3B -- and surpassing serveral closed-source agent workflows such as GPT-5 (42.9), Gemini-2.5 Pro (44.8), and Gemini-2.5 Flash (41.3).

Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT). However, the trial-and-error nature of RL, when conducted in real-world environments, is costly and hazardous in some scenarios. Consequently, the majority of RL research is conducted in simulation. This reliance introduces challenges related to the Sim-to-Real transferability. Evaluating the Sim-to-Real algorithmic robustness and the Sim-to-Real gap is a critical prerequisite for research aimed at improving RL performance in the real world. Therefore, industries such as robotics have developed concurrent simulation and physical platforms to facilitate this research. However, a universal Sim-to-Real benchmark platform for AIoT does not currently exist. To address these concerns, we developed a real-world AIoT platform for studying RL in AIoT. On this platform, an agent deployed on an edge device plays video games on a separate host computer via a hardware-emulated keyboard, guided by vision input. This platform uses commercially available components costing less than USD 400, together with two computers. Because the system's objective is game score maximization, it inherently mitigates safety risks associated with real-world RL deployments. Experimental results show the simulation-trained agent suffers a 1160% performance degradation relative to the human-level performance after real-world deployment, indicating a significant Sim-to-Real gap. Direct real-world training using the deep Q-network (DQN) algorithm achieves approximately 38% of human-level performance after 10 million training steps, demonstrating the feasibility of RL under real-world conditions. These results suggest that the proposed Sim-to-Real benchmark platform provides a substantial foundation for qualitative and quantitative evaluations of RL in real-world AIoT systems.

Starting from the utilization of deep neural networks to approximate the state-action value function that led to winning one of the most challenging games, to algorithmic advancements that allowed solving problems without even explicitly stating the rules of the challenge at hand, reinforcement learning research has been the center of remarkable scientific progress for the past decade. In this paper, we focus on the key ingredients of this research progress and we analyze the canonical evaluation and design paradigms in reinforcement learning. We introduce the theoretical foundations of scaling laws in reinforcement learning and show that the asymptotic performance of reinforcement learning algorithms does not have a monotone relationship between performance rankings and data-regimes. We conduct large-scale experiments and our results demonstrate that a line of reinforcement learning research under the canonical design and evaluation paradigms resulted in incorrect conclusions. Our analysis and results provide a core analysis on scaling, capacity and complexity of deep reinforcement learning.

Recent work trains reasoning models with length penalties to curb overthinking and cut inference cost. We show that these penalties make the chain of thought less monitorable. A length-compressed model still lets misleading hints steer its answers, but it less often verbalizes their influence. We train Qwen3-4B and Qwen3-14B with reinforcement learning under length penalties targeting 60% down to 30% of baseline chain-of-thought length, then evaluate them with nine types of biasing hints on held-out MMLU-Pro-R and four transfer benchmarks. A chain is faithful when an LLM monitor can tell from it that the hint influenced the answer. At the 30% target, accuracy stays near baseline and wrong-answer hints switch answers as often as before. Yet faithfulness drops on every evaluation set for both models, by 39% for Qwen3-14B and 35% for Qwen3-4B on MMLU-Pro-R. A control trained with the same correctness and format rewards but no length penalty leaves faithfulness intact or raises it. Shortening alone does not explain the drop. Compressed chains mention the hint 7 to 35 percentage points less often than the uncompressed model's chains shortened to the same length by random sentence deletion, across both model sizes and all five evaluation sets. Length penalties therefore trade monitorability for inference cost by removing the evidence monitors depend on.

Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems (CPSs) and robotics. A persistent challenge, however, is ensuring strict, hard safety constraints during the active learning phase. In real-world physical systems, violating mechanical limits can cause irreversible damage, necessitating that exploration remains strictly within safe operational regions. We propose a generalized framework that combines the adaptive, high-performance nature of deep reinforcement learning (DRL) with the formal safety guarantees of model predictive control (MPC). Using a mathematical model of the system dynamics, offline MPC computations define a feasible state-action space, representing all safe combinations of system states and control inputs that guarantee constraint satisfaction. During training and deployment, the RL agent's instantaneous actions are projected onto this globally verified feasible set via a safety filter. We systematically evaluate our generalized approach on a non-linear 1-DoF laboratory testbed, demonstrating successful exploration and stable policy convergence on physical hardware.

We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's minimalist 2D fighting game Footsies, it isolates the cyclic, non-transitive strategic interactions of fighting game neutral play while remaining simple enough for efficient analysis. We provide a vectorized simulator that enables high-throughput training on standard hardware, making the environment accessible and reproducible. We describe the design of the environment, benchmark several reinforcement learning algorithms, and discuss open research directions it enables. The code is available at https://github.com/como-research/FootsiesGym.

Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existing agentic post-training pipelines often treat data curation as a fixed preprocessing step, focusing mainly on data augmentation while neglecting filtering, refinement, and adaptation to downstream failures. We propose CurateEvo, a failure-driven dynamic evolution framework for agentic post-training data curation. CurateEvo represents the curation strategy as executable code and iteratively rewrites it using failed trajectories from a held-out development set. At each epoch, the evolved strategy transforms a fixed raw corpus into supervised fine-tuning data, reinforcement learning data, and an inference-time memory bank. The evolution process first improves effectiveness by diagnosing recurring failure modes and augmenting, filtering, or refining data accordingly, and then improves efficiency by pruning redundant or low-utility training turns under a cost-aware objective. Experiments on ACEBench-Agent, BFCL-V4, and τ^2-Bench under both labeled and wild-data settings show that CurateEvo consistently outperforms prior curation methods, improving average scores by 3.2 and 2.7 points, respectively. Further analyses demonstrate that CurateEvo is compatible with different post-training recipes and substantially reduces curation overhead.

In this paper, we investigate whether a model-free RL agent can identify and exploit price manipulation opportunities more effectively than a traditional model-based approach that assumes correct specification of the data-generating process but relies on noisy parameter estimates. We consider a single-asset market in which prices evolve according to an Almgren-Chriss framework with non-linear permanent impact and linear temporary impact. We first establish the existence of price-manipulative strategies in discrete time and compute the optimal benchmark strategy using Sequential Least Squares Quadratic Programming under full information. We then compare two finite-sample learning approaches: a model-based procedure that estimates impact parameters from simulated execution data and an agnostic RL approach based on Deep Deterministic Policy Gradient, trained directly on the same amount of data. For intermediate volatility, the RL agent successfully discovers profitable manipulative strategies without explicit knowledge of the underlying model, even when training data are quite limited. More importantly, RL consistently outperforms the model-based approach when parameter estimates are affected by sampling error, despite the latter benefiting from the correct model specification. For large volatility, all methods are unable to identify manipulation opportunities, while for small volatility, the model based approach outperforms RL. These findings highlight both the effectiveness of RL in complex control problems and the risks associated with deploying learning algorithms in financial markets without appropriate safeguards.

Portfolio optimization under uncertainty is inherently a multi-objective decision problem involving complex interactions among return, risk, market dynamics, and practical investment constraints. Existing reliability based portfolio optimization approaches primarily rely on static optimization frameworks and often fail to capture sequential decision making, tail risk, and market frictions such as transaction costs. To address these limitations, we propose a deep reinforcement learning framework for multi-objective reliability based portfolio optimization (MORP-DRL). The proposed framework jointly optimizes expected return and downside risk using three complementary risk measures: variance, Conditional Value-at-Risk (CVaR), and Entropic Value-at-Risk (EVaR). To model uncertainty and heavy-tailed market behavior, asset returns are represented using GARCH(1,1), Extreme Value Theory, and a t-copula dependence structure, while realistic scenarios are generated through quasi-Monte Carlo simulation. A Proximal Policy Optimization (PPO) based strategy is developed under practical constraints including transaction costs and portfolio bounds, and is benchmarked against NSGA-II. Experiments on ten global equity indices across pre-COVID, COVID, and post-COVID market regimes demonstrate that MORP-DRL achieves competitive risk-return performance, reduced downside risk during periods of market stress, and scalability to high-dimensional portfolio settings.

Battery charging of Autonomous Mobile Robots (AMRs) in warehouses is a critical operational challenge that heavily impacts both order processing times and throughput. In this study, we address the dynamic AMR charging problem under stochastic order arrivals, where robots must learn optimal charging decisions. Traditional fixed-rule heuristics often prove suboptimal in dynamic environments and fail to account for multi-AMR coordination, leading to severe resource inefficiencies. To overcome these limitations, we propose a Proximal Policy Optimization (PPO)-based Deep Reinforcement Learning (DRL) framework designed for multi-block warehouses with fixed charging stations. Our model dynamically learns two key decisions: charging station selection and optimal charging duration, explicitly accounting for anticipated queuing times at the stations. Extensive numerical experiments benchmark the proposed model against state-of-the-art DRL and traditional heuristic approaches. Results demonstrate that our PPO framework increases order-completion rates by up to 6% compared to the strongest baseline, while significantly reducing the total time dedicated to recharging operations. Furthermore, we validate the model's robustness across diverse warehouse configurations and stochastic arrival rates. Finally, we interpret the learned DRL policy, offering valuable operational insights into its superiority over standard benchmarks.

Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck. We study a weak-to-strong alternative: run RL on a smaller model where rollouts are cheaper, then reuse what that RL run learned to improve a stronger target model. Directly distilling the post-RL weak teacher is not enough, because the teacher's final policy mixes useful RL gains with the limitations of the smaller model. We propose Direct On-Policy Distillation (Direct-OPD), which transfers the teacher's RL-induced policy shift instead. Direct-OPD compares the post-RL teacher with its own pre-RL reference and treats their log-ratio as a dense implicit reward for the student. In plain terms, the checkpoint pair tells us which actions RL made the weak model more or less likely to take, and Direct-OPD applies that signal on the stronger student's own on-policy states. This directly reuses the weak model's RL supervision signal without running sparse-reward RL on the target model. Empirically, Direct-OPD consistently leverages weaker teachers to improve stronger target models; notably, it boosts Qwen3-1.7B from 48.3% to 58.3% on AIME 2024 in just 4 hours on 8 A100 GPUs. It outperforms step-matched direct RL and enables the sequential composition of multiple policy shifts. Our results show that RL outcomes can be reused across model scales as implicit reward signals, not merely as final models to imitate.

In liberalised railway systems, operators must set prices dynamically in an environment with partial observability, as they retain private information about their objectives and performance, where regulatory constraints prohibit communication or direct information exchange between competitors to prevent explicit collusion. Consequently, agents must learn to infer strategic interactions only from observable market data which presents a significant challenge for multi-agent reinforcement learning, where standard approaches typically treat observations as unstructured vectors, ignoring the underlying market topology that governs strategic interactions. To address this, an entity graph modelling approach is proposed, which represents the environment as a graph of operational units, rather than decision-making agents or static infrastructure, encoding competition, coordination, and connectivity relations between entities. Then, an extension of the multi-agent twin delayed deep deterministic policy gradient algorithm with graph-based representation learning processes the features of the entities through a multi-layer relational graph convolutional network and aggregates them via a learnt attention mechanism. Experimental results in a rail pricing reinforcement learning environment show that this novel framework achieves higher revenue and stability in two different settings of increasing market complexity compared to a representative selection of relational and non-relational baselines. The code is publicly available at: https://github.com/Kinrre/RelationalRailPricing-RL

Vision-based deep reinforcement learning involves dealing with high-dimensional inputs of image information. It is crucial to abstract effective states from high-dimensional image inputs and limited samples for sample-efficient reinforcement learning. To address this challenge, inspired by fields such as natural language processing and computer vision, we propose a self-supervised task based on mask prediction as an auxiliary task for reinforcement learning. This non-reconstruction method uses the sequence information collected by the agent from the environment and the context information in the sequence to predict the masked information, thereby strengthening the agent's understanding of the task and learning effective representations. Combined with transformers, we find that the model reconstructs the masked input sequence in the latent space. By feeding the compressed representations learned by this method into reinforcement learning models, we observe an improvement in the sample efficiency of reinforcement learning. Moreover, the model outperforms state-of-the-art sample-efficient reinforcement learning methods on multiple continuous and discrete control benchmarks.

Current agentic workflows usually involve decomposing user requests into sequences of tool calls with correctly resolved parameters, the results of which are processed through reasoning traces in the language model's context window. The prevailing route to improve such reasoning is test-time scaling, which trains models to search over long chains of thought; but the resulting capability is entangled in model weights, is not verifiable step-by-step, and is costly at inference. We present Forethought, a neurosymbolic reasoning system that instead treats reasoning as an explicit, verifiable program, that builds from a library of symbolic and neural primitives which are composed through a domain-specific language. The result are reasoning programs, which are concrete representations of the model's work, and as such can be inspected and modified before deployment. Instantiated as a tool-calling execution kernel and evaluated across five benchmarks, Forethought improves base-model accuracy by about 30% relative and outperforms vanilla prompting, reinforcement learning scaffolds, and prompt-evolution methods, enabling small models to match or exceed frontier models capabilities. In a direct comparison, a non-reasoning model augmented with Forethought competes with a dedicated reasoning model while requiring roughly three orders of magnitude less post-training investment, and remains model-agnostic and auditable.

This study independently replicates and extends the Natural Language Tools (NLT) framework of Johnson et al.~(2025), which questions the use of structured tool calling in large language model (LLM) agentic systems. We evaluated NLT across 14 models and 8,560 trials, adding newer frontier, reasoning, and open-weight models to the original set. The results confirm the core findings and add detail. NLT improves tool-calling accuracy by 14.9 percentage points overall (62.3% versus 47.4% structured) and reduces critical errors by 93% (51 versus 755 errors). The gains depend on model capability: models without native tool calling, reasoning models, and smaller models gain substantially (+24.0pp to +43.1pp), while heavily optimized frontier models (GPT-5, Gemini 2.5 Pro) show smaller or reversed advantages. This matches recent analyses of reinforcement-learning-optimized tool use (Martinez, 2025). NLT also cuts token usage by 25.2%. The reliability and efficiency advantages compound in recursive agentic workflows, where agents chain many tool calls across sub-agents: a structured failure triggers retries, fallback routing, and coordination overhead, while NLT avoids most of that cost at the source. This work makes three contributions: (1) the first independent validation of NLT using open-source tooling, (2) evidence that model capability moderates NLT's advantages (Chen et al., 2025; Zhang et al., 2025), and (3) a measurement of NLT's reliability benefit (93% fewer errors), its most deployment-relevant property given the known fragility of structured tool calling. NLT is a practical alternative to structured tool calling, especially for production systems that value reliability over parseability.

Reinforcement Learning (RL) has emerged as a powerful paradigm for adaptive traffic signal control. However, in safety-critical infrastructure like traffic control, the opaque, black-box nature of deep RL models poses challenges for transportation agency acceptance, regulatory compliance, operational trust, troubleshooting, and fine-tuning. To bridge this gap between high-performance optimization and human-comprehensible interpretability, this effort introduces a novel, explainable entity centric RL framework for safe and transparent traffic signal control. Rather than processing traffic states through monolithic, flat vectors, the proposed architecture disaggregates real-time intersection observations into distinct, high-dimensional lane entities and phase temporal configurations to inherently preserve the structural topology and geometric configurations of the intersection. Relational dependencies and inter-lane conflicts are dynamically extracted via a dual-stage attention network featuring sequential multi-head cross-attention and self-attention blocks. This design yields a real time affinity matrix that quantifies the direct influence of signal phases on specific approach volumes and queues, providing full visual and analytical interpretability. To ensure strict operational reliability, a deterministic action-masking interface is integrated directly into the Proximal Policy Optimization pipeline, explicitly blocking invalid phase transitions to guarantee absolute compliance with established signal timing and safety constraints. Evaluated in a microscopic simulation environment, outperforms state-of-the-art baselines in delay minimization. More importantly, the emergent attention weights align precisely with established traffic engineering principles, offering an auditable, trust-enabling, and deployable architecture for next-generation adaptive traffic control systems.

Large language model (LLM) agents have shown strong decision-making capabilities in long-horizon interactive tasks, yet they still struggle to effectively leverage failed trajectories: full retries incur high interaction costs, while experience retrieval tends to dilute critical experience signals. To address this, we propose PivoARL, a self-feedback retry framework for experience exploitation in LLM agents. PivoARL identifies the pivotal erroneous turn through structured reflection and performs local retry only from the corresponding pivotal state, thereby reusing the correct prefix and reducing redundant interactions. From an information-gain perspective, we further show that pivotal retry concentrates useful experience signals near the error boundary, mitigating the signal dilution caused by state-agnostic experience utilization. Based on this insight, we design a pivotal-aware credit assignment mechanism that rewards correct prefixes while isolating erroneous suffixes, and optimize reflection quality through implicit reflection returns. We conduct a systematic evaluation on 4 agent tasks and 7 search-based QA benchmarks. Results show that PivoARL achieves significant improvements on Pass@2/3 across all tasks, with an average gain of about 11.5% over MetaRL. Moreover, benefiting from contrastive preference signals induced by pivotal turns, PivoARL also consistently improves Pass@1 on over 80% of the tasks. On Minesweeper environment, PivoARL improves over GiGPO by more than 45% and reduces interaction turns by about 42% on average compared with full-retry methods. Code is available at https://github.com/yuki-younai/PivoARL.

Deep reinforcement learning (DRL) in industrial control often suffers from lag and overshoot due to purely reactive control based on the current tracking error. To achieve anticipatory control without high computational overhead, we introduce a predictive formulation that augments the DRL state space with target velocities and future reference horizons. Evaluating eight configurations using proximal policy optimization (PPO) on a 1-degree-of-freedom (1-DoF) helicopter testbed, simulation results showed a 9-fold error reduction, lowering the mean absolute deviation from 2.73° to 0.31°. However, zero-shot transfer to physical hardware revealed a sim-to-real gap. Interestingly, a simpler configuration using a single, further look-ahead horizon matched the real-world top performance of the most complex model (1.11°). Overall, evaluating various combinations of prediction horizons and target velocities demonstrated that highly granular predictive data is not necessarily required for physical transfer.