Soft Actor-Critic

Grounded multi-video question answering over real-world news events requires systems to surface query-relevant evidence across heterogeneous video archives while attributing every claim to its supporting source. We introduce CRAFT (Critic-Refined Adaptive Key-Frame Targeting), a query-conditioned pipeline that combines dynamic keyframe selection, per-video ASR with multilingual fallback, and a hybrid critic loop to iteratively verify and repair claims before consolidation. The pipeline integrates UNLI temporal entailment, DeBERTa-v3 cross-claim screening, and a Llama-3.2-3B adjudicator, with a final citation-merging stage that emits each fact once with all supporting source identifiers. On MAGMaR 2026, CRAFT achieves the best overall average (0.739), reference recall (0.810), and citation F1 (0.635). We further evaluate on a MAGMaR-style conversion of WikiVideo with 52 non-overlapping event queries, where CRAFT also performs strongly (0.823 Avg), showing that its claim-centric evidence aggregation generalizes beyond MAGMaR. Ablations show that atomic claims, ASR, and the critic loop drive the main gains over the vanilla query-conditioned baseline. Code and implementation details are publicly available at https://github.com/bhosalems/CRAFT.

This paper proposes a Shared Backbone Proximal Policy Optimization (Shared Backbone PPO) algorithm. By sharing the base module between the Actor and Critic networks, the algorithm achieves efficient training and improved performance. The algorithm is implemented in a connectivity-preserving multi-UAV swarm communication coverage task and compared with the standard PPO algorithm. Experimental results demonstrate that the proposed method achieves superior performance. Furthermore, a graph information aggregation module is incorporated into the model architecture to accommodate the communication conditions among agents. With the integration of this module, the algorithm remains effective, and the trained agent swarm exhibits a higher level of cooperation.

We address the discounted reward setting in reinforcement learning (RL). To mitigate the value approximation challenges in policy gradient methods, actor-critic approaches have been developed and are known to converge to stationary points under suitable assumptions. However, these methods rely on first-order updates. In contrast, second-order optimization provides principled curvature-aware updates that are proven to accelerate convergence, but its application in RL is limited by the computational complexity of Hessian estimation. In this work, we analyze second-order approximations for the actor update that leverage the full curvature information of the objective as much as possible. A stable approximation requires treating the action-value function as locally constant with respect to policy parameters, which does not generally hold in policy gradient methods. We show that this approximation becomes well-justified under a two-timescale actor-critic framework, where the critic evolves on a faster timescale and can be treated as quasi-stationary during actor updates. Building on this insight, we formulate a second-order actor-critic method for the discounted reward setting that leverages Hessian-vector product (HVP) computations, resulting in a computationally efficient and stable second-order update.

Despite many successful attempts at explaining Deep Reinforcement Learning policies using distillation, it remains difficult to balance the performance-interpretability trade-off and select a fitting surrogate model. In addition to this, traditional distillation only minimizes the distance between the behavior of the original and the surrogate policy while other RL-specific components such as action value are disregarded. To solve this, we introduce a new model-agnostic method called Critic-Driven Voronoi State Partitioning, which partitions a black box control policy into regions where a simple class of model can be optimized using gradient descent. By exploiting the critic value network of the original policy, we iteratively introduce new subpolicies in regions with insufficient value, standing in for a measure of policy complexity. The partitioning, a Voronoi quantizer, uses nearest neighbor lookups to assign a linear function to each point in the state space resulting in a cell-like diagram. We validate our approach on several well known benchmarks and proof that this distillation approaches the original policy using a reasonable sized set of linear functions.

Despite the popularity of the actor-critic method and the practical needs of collaborative policy training, existing works typically either overlook environmental heterogeneity or give up personalization altogether by training a single shared policy across all agents. We consider a federated actor-critic framework in which agents share a common linear subspace representation while maintaining personalized local policy components, and agents iteratively estimate the common subspace, local critic heads, and local policies (i.e., actors). Under canonical single-timescale updates with Markovian sampling, we establish finite-time convergence via a novel joint linear approximation framework. Specifically, we show that the critic error converges to zero at the rate of $\tilde{\mathcal{O}}(1/((1-γ)^4\sqrt{TK}))$, and the policy gradient norm converges to zero at the rate of $\tilde{\mathcal{O}}(1/((1-γ)^6\sqrt{TK}))$, where $T$ is the number of rounds, $K$ is the number of agents, and $γ\in (0,1)$ is the discount factor. These results demonstrate linear speedup with respect to the number of agents $K$, despite heterogeneous Markovian trajectories under distinct transition kernels and coupled learning dynamics. To address these challenges, we develop a new perturbation analysis for the projected subspace updates and QR decomposition steps, together with conditional mixing arguments for heterogeneous Markovian noise. Furthermore, to handle the additional complications induced by policy updates and temporal dependence, we establish fine-grained characterizations of the discrepancies between function evaluations under Markovian sampling and under temporally frozen policies. Experiments instantiate the framework within PPO on federated \texttt{Hopper-v5} action-map heterogeneity, showing gains over Single PPO and FedAvg PPO and downstream transfer from the learned shared trunk.

Test-Time Scaling (TTS), which samples multiple candidate actions and ranks them via a Critic Model, has emerged as a promising paradigm for generalist GUI agents. Its efficacy thus hinges on the critic's fine-grained ranking ability. However, existing GUI critic models uniformly adopt binary classification. Our motivational analysis of these models exposes a severe entanglement: scores for valid actions and plausible-but-invalid distractors become indistinguishable. We attribute this failure to two structural defects: Affordance Collapse--the hierarchical affordance space is compressed into 0/1 labels; and Noise Sensitivity--binary objectives overfit to noisy decision boundaries. To resolve this, we introduce BBCritic (Beyond-Binary Critic), a paradigm shift grounded in the Functional Equivalence Hypothesis. Through two-stage contrastive learning, BBCritic aligns instructions and actions in a shared Affordance Space, recovering the hierarchical structure that binary supervision flattens. We also present BBBench (Beyond-Binary Bench), the first GUI critic benchmark that pairs a dense action space with a hierarchical four-level taxonomy, enabling fine-grained ranking evaluation. Experimental results show that BBCritic-3B, trained without any extra annotation, outperforms 7B-parameter SOTA binary models. It demonstrates strong zero-shot transferability across platforms and tasks, supporting our methodological view: GUI critique is fundamentally a metric-learning problem, not a classification one.

In this paper, we establish last-iterate convergence rates for off-policy actor--critic methods in reinforcement learning. In particular, under a single-loop, single-timescale implementation and a broad class of policy updates, including approximate policy iteration and natural policy gradient methods, we prove the first $\tilde{\mathcal{O}}(ε^{-2})$ sample complexity guarantee for finding an $ε$-optimal policy under minimal assumptions, namely, the existence of a policy that induces an irreducible Markov chain. This stands in stark contrast to the existing literature, where an $\tilde{\mathcal{O}}(ε^{-2})$ sample complexity is achieved only through nested-loop updates and/or under strong, algorithm-dependent assumptions on the policies, such as uniform mixing and uniform exploration. Technically, to address the challenges posed by the coupled update equations arising from the single-loop implementation, as well as the potentially unbounded iterates induced by off-policy learning, our analysis is based on a coupled Lyapunov drift framework. Specifically, we establish a geometric convergence rate for the actor and an $\tilde{\mathcal{O}}(1/T)$ convergence rate for the critic, and combine the two Lyapunov drift inequalities through a cross-domination property. We believe this analytical framework is of independent interest and may be applicable to other coupled iterative algorithms with unbounded

Instruction-based image editing exhibits heterogeneous difficulty not only across cases but also across regions of an image, motivating refinement approaches that allocate correction to where the model struggles. Existing refinement signals arrive late, after a fully generated image or a completed denoising step. We ask whether such a signal can act within an ongoing forward pass. To investigate this, we probe a frozen image-editing model and find that although generation capability emerges only in the last few layers, the error pattern is already set in early layers (rank correlation \r{ho} = 0.83 with the final-layer error map). Based on this, we introduce Inline Critic, a learnable token that critiques a frozen model's predictions at its intermediate layers and steers its hidden states to refine generation during the forward pass. A three-stage recipe is proposed to stabilize the training from learning how to critique to steering generation. As a result, we achieve state of the art on GEdit-Bench (7.89), a +9.4 gain on RISEBench over the same backbone, and the strongest open-source result on KRIS-Bench (81.92, surpassing GPT-4o). We further provide analyses showing that the critic genuinely shapes the model's attention and prediction updates at subsequent layers.

Vision Transformers (ViTs) incur significant computational overhead due to the quadratic complexity of self-attention relative to the token sequence length. While existing token reduction methods mitigate this issue, they predominantly rely on fixed heuristic metrics, predefined ratios, or static offline masks, which lack the adaptability to capture input-dependent redundancy during inference. In this paper, we propose DORA (Dynamic Online Reinforcement Agent), the first reinforcement learning (RL)-driven online inference framework for dynamic token merging in ViTs. We formulate the merging process as a sequential Markov Decision Process (MDP), where a lightweight RL agent determines the merging strategy for each Transformer block based on the current feature state and layer-specific context. To balance computational efficiency and feature fidelity, the agent is optimized via a dense reward function incorporating a non-linear distillation-based penalty. We implement an asymmetric Actor-Critic architecture that utilizes a high-capacity Critic for stable offline training while retaining a minimal Actor head for low-computation online inference. Evaluations across multiple ViT scales (Tiny to Large) demonstrate that DORA improves the accuracy-efficiency Pareto front compared to current baselines. Under strict negligible accuracy-drop constraints (<= 0.05%), DORA achieves up to a 12.66% token merging rate, and delivers up to a 569.7% relative improvement over the most efficient baseline. On ImageNet-1K, under aligned accuracy constraints, DORA achieves up to a 76% relative improvement in computational savings compared to state-of-the-art methods. Furthermore, on out-of-distribution (OOD) benchmarks such as ImageNet-A and ImageNet-C, DORA attains a relative efficiency advantage of over 430%.

Soft Actor-Critic (SAC) and its variants dominate Multi-Task Reinforcement Learning (MTRL) due to their off-policy sample efficiency, while on-policy methods such as Proximal Policy Optimization (PPO) remain underexplored. We diagnose that PPO in MTRL suffers from a previously overlooked issue: critic-side gradient ill-conditioning, which may cause tail tasks to stall while easy tasks dominate the value function's updates. To address this, we propose TOPPO (Tail-Optimized PPO), a reformulation of PPO via Critic Balancing -- a set of modules that improve gradient conditioning and balance learning dynamics across tasks. Unlike prior approaches that rely on modular architectures or large models, TOPPO targets the optimization bottleneck within PPO itself. Empirically, TOPPO achieves stronger mean and tail-task performance than published SAC-family and ARS-family baselines while using substantially fewer parameters and environment steps on Meta-World+ benchmark. Notably, TOPPO matches or surpasses strong SAC baselines early in training and maintains superior performance at full budget. Ablations confirm the effectiveness of each module in TOPPO and provide insights into their interactions. Our results demonstrate that, with proper optimization, on-policy methods can rival or exceed off-policy approaches in MTRL, challenging the prevailing reliance on SAC and highlighting critic-side gradient conditioning as the central bottleneck.

For reinforcement learning in the real world online exploration is expensive A common practice in robotic reinforcement learning is to incorporate additional data to improve sample efficiency Expert demonstration data is often crucial for solving hard exploration tasks with sparse rewards While prior data is used to augment experience and pretrain models we show that the design of existing algorithms fails to achieve the sample efficiency that is possible in this setting due to a failure to use pretrained policies effectively We propose XQCfD which extends the sample-efficient XQC actor-critic to learn from demonstrations using augmented replay buffers pretrained policies and stationary policy architectures designed to avoid rapidly unlearning the strong initial policy like prior works We show our stationary network architecture enables policy improvement out-of-distribution better than standard network architectures due to its higher entropy predictions XQCfD achieves state of the art performance across a range of complex manipulation tasks with sparse rewards from the popular Adroit Robomimic and MimicGen benchmarks -- notably with a low update-to-data ratio and no ensemble networks

Large language models can fail in critic interaction not only by answering incorrectly, but also by abandoning an initially correct scientific solution after user criticism. This is especially risky in scientific reasoning, where user criticism can turn a valid answer into an incorrect one. We frame critic interaction as an inter-turn correctness-transition problem rather than a final-answer accuracy problem, and identify three challenges: transition awareness, decoupling useful correction from harmful sycophancy, and scalable rollout. We propose ReCrit, a transition-aware reinforcement learning framework that decomposes Initial-to-Critic behavior into four quadrants: Correction, Sycophancy, Robustness, and Boundary. ReCrit rewards correction and robustness, penalizes sycophancy, and treats persistent errors as weak boundary signals. To make interaction training practical, ReCrit further uses dynamic asynchronous rollout with tail-adaptive completion to reduce rollout waiting. On three scientific reasoning benchmarks, ChemBench, TRQA, and EarthSE, ReCrit improves average Critic accuracy from 38.15 to 51.49 on Qwen3.5-4B and from 45.40 to 55.59 on Qwen3.5-9B. Ablations show that final-answer rewards provide little interaction-level gain, while transition-aware rewards and quadrant weighting produce more distinguishable training signals and larger net Critic-stage improvement. The code is available at https://github.com/black-yt/ReCrit .

Long-horizon, sparse-reward tasks pose a fundamental challenge for reinforcement learning, since single-step TD learning suffers from bootstrapping error accumulation across successive Bellman updates. Actor-critic methods with action chunking address this by operating over temporally extended actions, which reduce the effective horizon, enable fast value backups, and support temporally consistent exploration. However, existing methods rely on a fixed chunk size and therefore cannot adaptively balance reactivity against temporal consistency. A large fixed chunk size reduces responsiveness to new observations, while a small one produces incoherent motions, forcing task-specific tuning of the chunk size. To address this limitation, we propose Adaptive Chunk Size Actor-Critic (ACSAC). ACSAC leverages a causal Transformer critic to evaluate expected returns for action chunks of different sizes. At each chunk boundary, it adaptively selects the chunk size that maximizes the expected return, supporting flexible, state-dependent chunk sizes without task-specific tuning. We prove that the ACSAC Bellman operator is a contraction whose unique fixed point is the action-value function of the adaptive policy. Experiments on OGBench demonstrate that ACSAC achieves state-of-the-art performance on long-horizon, sparse-reward manipulation tasks across both offline RL and offline-to-online RL settings.

Mixture policies theoretically offer greater flexibility than unimodal policies in continuous action reinforcement learning, but the practical benefits of this complexity remain elusive. Mixture policies are notably absent from most state-of-the-art algorithms, raising a fundamental question: Is the added representational overhead useful? We show that increased flexibility can theoretically enhance solution quality and entropy robustness. Yet standard algorithms like SAC do not leverage these advantages. A core issue is the lack of a low-variance reparameterization trick for mixtures, a luxury Gaussian policies enjoy. We propose a marginalized reparameterization (MRP) estimator to address this, proving it offers lower variance than the standard likelihood-ratio (LR) approach. Our experiments across Gym MuJoCo, DeepMind Control Suite, and MetaWorld show that MRP mixture policies significantly outperform their LR ones, and reach parity (sometimes better) with Gaussian counterparts. In addition, we do find several cases where MRP mixture policies exhibit clear empirical advantages. In this paper, we provide a clearer understanding of the trade-offs involved, elevating MRP mixture policies from theoretical curiosity to a practical tool.

Expressive generative policies such as diffusion and flow models are appealing for MaxEnt online reinforcement learning because of their ability to model multimodal and highly non-Gaussian action distributions. However, training effective soft generative policies faces two obstacles that often arise together. First, marginal action densities are often unavailable, so existing methods typically rely on entropy bounds, heuristic proxies or approximations. Second, iterative shared-parameter samplers raise inference cost and require backpropagation through time over repeated network evaluations, increasing memory cost and destabilizing policy optimization. These obstacles motivate us to seek a generative policy that exposes a tractable MaxEnt objective while requiring only a single sampled actor forward pass for action generation. To this end, we propose soft generative actor-critic (SoftGAC), whose actor defines a stochastic bridge from a fixed base latent to a terminal action latent in pre-tanh space. This structured bridge allows us to lift the MaxEnt objective as an analytically tractable path-wise relative-entropy objective against a high-entropy reference process. In practical finite-step implementation, this relative entropy reduces exactly to sampled transition control energy and thus provides principled soft regularization. Moreover, we keep the single-pass actor lightweight by using small step-specific bridge transitions, each evaluated only once per sampled action, while maintaining a parameter budget comparable to strong actor baselines. Extensive experiments on challenging continuous-control benchmarks show that SoftGAC attains higher or competitive returns than strong generative policy baselines, including diffusion and flow-matching policies, while staying in the low-latency regime of one-pass actors and showing considerable improvements in the compute-return tradeoff.

Standard rational actor models often attribute cooperation failures in social dilemmas to insufficient incentives, overlooking the destabilizing effects of continuous utility maximization. To address this, we propose a framework of will" defined as a mechanism that persistently pursues goals while ignoring local cost-benefit fluctuations. We formalize the Willed Agents as potential minimizers, distinguishing them from cumulative utility maximization. Dynamical analysis of infinite population demonstrates that willed agents shrink the feasible state space, acting as boundary constraints that accelerate convergence in canonical social dilemmas. Through multi-agent simulations in a spatiotemporal Stag Hunt Game, we show that willed agents function as cooperation catalysts", enabling groups to surmount high-risk thresholds where purely utility maximization fails. We find that heterogeneous will strength promotes cooperation, and that agents who autonomously suspend rational re-evaluation can significantly outperform continuous optimizers. These findings suggest that successful cooperation relies on the cognitive capacity to strategically constrain calculation.

A commonly accepted explanation of critic-free RL for LLMs, based on sequence-level rewards, is that it reinforces successful rollouts with a positive advantage while penalizing failed ones. In contrast, we study critic-free RL from a token-level perspective, revealing the token-flipping phenomenon: positive and negative rollouts exhibit remarkably similar proportions of tokens whose probabilities are boosted or suppressed during RL training. To explain this phenomenon, we further show that a token's change in probability is not fully determined by its own advantage; coupled gradient interactions with other tokens also play a non-negligible role. Specifically, these token coupling effects occur primarily between identical tokens that are both predicted with low confidence. Building upon this analysis, we propose the cancellation hypothesis: as a result of coupling, opposing signals cancel out for tokens shared by positive and negative rollouts, while tokens more specific to successful rollouts receive stronger reinforcement, thereby inducing hidden token-level credit assignment from rollout-level rewards. We support this hypothesis with complementary empirical evidence. (1) Compared with training on only positive rollouts, critic-free RL shifts updates from template and formatting tokens toward reasoning tokens; (2) Tokens boosted by critic-free RL consistently demonstrate higher value than suppressed tokens, regardless of whether they originate from positive or negative rollouts. Guided by this view, we implement two batching interventions to encourage or preserve cancellation in critic-free RL training: query-preserved mini-batching and reward-balanced batching. Despite their simplicity, these interventions improve RLVR training across multiple model scales, supporting cancellation as both an explanatory principle and a practical design criterion for critic-free RL training.

Optimizing dynamic risk with stochastic policies is challenging in both policy updates and value learning. The former typically requires transition perturbation, while the latter may rely on model-based approaches. To address these challenges, we propose a surrogate policy gradient without transition perturbation under softmax policy parameterization. We further develop model-free value learning methods for dynamic expectile and conditional value-at-risk by leveraging elicitability. Finally, inspired by Expected SARSA and Expected Policy Gradient, a model-free off-policy actor-critic algorithm is constructed. Empirical results in domains with verifiable risk-averse behavior show that our algorithm can learn risk-averse policy and consistently outperforms other existing methods.

This paper introduces the Active-Importance-Sampling Actor-Critic (AISAC) algorithm, an extension of the Actor-Critic framework for reducing variance in policy gradient estimation. AISAC optimizes the behavior policy to minimize gradient variance while preserving unbiased gradient estimates. Using importance sampling principles, the algorithm adapts the behavior policy toward efficient data collection distributions aligned with target policy gradients. For continuous action spaces, AISAC employs Gaussian behavior policies optimized through cross-entropy minimization. We provide theoretical analysis demonstrating variance reduction and unbiasedness. Experiments on Inverted Pendulum and Half Cheetah tasks show improved learning speed, sample efficiency, and training stability compared to standard Actor-Critic methods. Results indicate that optimizing the behavior policy improves both target policy updates and critic estimation accuracy across different hyperparameter settings. AISAC accelerates convergence and stabilizes reinforcement learning training, making it promising for real-world applications. Future work includes integration with advanced algorithms such as Soft Actor-Critic and TD3 for more complex environments.

We augment the Slotine--Li adaptive controller for Euler--Lagrange systems with three learned components: a structured-quadratic Lyapunov function $V_ψ$ whose positive-definiteness follows from a Cholesky parameterization, a residual Soft Actor--Critic policy that adds bounded torque corrections to the analytic baseline, and a physics-informed neural network that estimates unmodeled dynamics. A closed-form safety filter, derived from the single affine constraint $\dot V_ψ+ αV_ψ\le 0$, projects every policy output onto the safe set without requiring an online QP solver. We prove: global feasibility of the filter under a drift-decay condition on the control-degeneracy set; exponential stability under exact shielding, with a robust extension whose margin depends on the PINN approximation error; almost-sure convergence of the three-timescale policy--certificate--multiplier updates to a KKT point; and a PAC generalization bound for the certificate over compacts. On a 2-DOF manipulator with nonlinear friction and variable payload, the learned certificate accounts for most of the empirical gain: tracking error drops by 41% on nominal friction and 24% on aggressive friction at the centroid of the training distribution. A 7-DOF scalability study on a Franka Emika Panda confirms clean convergence of the full pipeline at industrial scale, identifies the conditions under which gains over exact model-based baselines should and should not be expected, and documents a warm-start pathology of the learned certificate that has practical implications for deployment.

As large language models (LLMs) show increasing promise on research-level physics reasoning tasks and agentic AI becomes more common, a practical question emerges: How does the interaction between researchers and agents affect the results? We study this using SCALAR (Structured Critic--Actor Loop for AI Reasoning), an Actor--Critic--Judge pipeline applied to quantum field theory and string theory problems. The Actor proposes solutions, the Critic provides iterative feedback, and an independent Judge evaluates the transcript against reference solutions. We vary the Actor persona, the Critic feedback strategy, and the Actor model family and scale. Multi-turn dialogue improves over single-shot attempts throughout, but both the mechanism of improvement and the value of different prompting choices depend strongly on the Actor--Critic pairing. Increasing the scale within one model family (e.g. from the 8B-parameter DeepSeek-R1 variant to DeepSeek-R1 70B) improves some easier-problem behavior, but does not remove the hardest bottleneck we observe. Critic feedback strategy matters most clearly in the asymmetric Actor--Critic setting (e.g., a lightweight Haiku Actor guided by a stronger Sonnet Critic), where constructive feedback improves mean-score outcomes. In same-family Actor--Critic settings, strategy effects are weaker: lenient feedback is sometimes favored, while strict and adversarial feedback are not beneficial. Taken together, SCALAR provides a controlled testbed for evaluating which interaction structures help or hinder AI-driven scientific discovery.

Robust embodied navigation relies on complementary sensory cues. However, high-quality and well-aligned multi-modal data is often difficult to obtain in practice. Training a monolithic model is also challenging as rich multi-modal inputs induce complex representations and substantially enlarge the policy space. Cross-modal collaboration among lightweight modality-specialized agents offers a scalable paradigm. It enables flexible deployment and parallel execution, while preserving the strength of each modality. In this paper, we propose \textbf{CRONA}, a Multi-Agent Reinforcement Learning (MARL) framework for \textbf{Cro}ss-Modal \textbf{Na}vigation. CRONA improves collaboration by leveraging control-relevant auxiliary beliefs and a centralized multi-modal critic with global state. Experiments on visual-acoustic navigation tasks show that multi-agent methods significantly improve performance and efficiency over single-agent baselines. We find that homogeneous collaboration with limited modalities is sufficient for short-range navigation under salient cues; heterogeneous collaboration among agents with complementary modalities is generally efficient and effective; and navigation in large, complex environments requires both richer multi-modal perception and increased model capacity.

Deterministic policy gradient (DPG) is widely utilized for continuous control; however, it inherently relies on the differentiability of the critic with respect to the action during policy updates. This assumption is violated in practical control problems involving sparse or discrete rewards, leading to ill-defined policy gradients and unstable learning. To address these challenges, we propose a principled alternative based on a smoothed Bellman equation formulated via Gaussian smoothing. Specifically, we define a novel action-value function based on a smoothed Bellman equation and derive the soft deterministic policy gradient (Soft-DPG). Our formulation eliminates explicit dependence on critic action-gradients and ensures that the gradient remains well-defined even for non-smooth Q-functions. We instantiate this framework into a deep reinforcement learning algorithm, which we call soft deep deterministic policy gradient (Soft DDPG). Empirical evaluations on standard continuous control benchmarks and their discretized-reward variants show that Soft DDPG remains competitive in dense-reward settings and provides clear gains in most discretized-reward environments, where standard DDPG is more sensitive to irregular critic landscapes.

The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL methods use a single fixed value across all states. While state-dependent discounting is conceptually appealing, naive deep actor--critic implementations can become unstable and degenerate toward TD-error collapse. We propose AdaGamma, a practical deep actor--critic method for state-dependent discounting that learns a state-dependent discount function together with a return-consistency objective to regularize the induced backup structure. On the theory side, we analyze the Bellman operator induced by state-dependent discounting and establish its basic well-posedness properties under suitable conditions. Empirically, AdaGamma integrates into both SAC and PPO, yielding consistent improvements on continuous-control benchmarks, and achieves statistically significant gains in an online A/B test on the JD Logistics platform. These results suggest that state-dependent discounting can be made effective in deep RL when coupled with a return-consistency objective that prevents degenerate target manipulation.

Agentic artificial intelligence systems produce outputs through sequences of interdependent autonomous decisions, yet standard evaluation assesses outputs alone and cannot diagnose the underlying process. We develop a behavioral evaluation methodology that complements output-level testing by scoring the intermediate decision process itself. Behavioral traces logged at each autonomous decision point are grouped into five-day episodes and scored along six domain-specific dimensions (regime detection, routing, adaptation, risk calibration, strategy coherence, error recovery) by an ensemble of three large language model (LLM) judges. A perturbation procedure that corrupts one dimension while leaving the other five intact confirms dimension specificity; cross-model agreement reaches Krippendorff's alpha = 0.85. The composite behavioral score correlates at Spearman rho = 0.72 with realized 20-day Sharpe ratio. Closing the loop, the framework converts deficient per-dimension scores into a credit-assigned penalty added to the Soft Actor-Critic reward. Three fine-tuning cycles, confined to validation data, reduce one-day MAPE from 0.61% to 0.54% (11.5% relative; p<0.001, d=0.31) on the held-out 2017 to 2025 test period, significant under Diebold-Mariano and localized by Giacomini-White to the high-volatility regime. The methodology is application-agnostic and applies to any agentic system whose intermediate decisions can be logged.

While parameterized quantum computations have shown success in standard reinforcement learning (RL), whether these advantages adapt to hierarchical RL (HRL) remains a critical open question. This work demonstrates that variational quantum circuits (VQCs) can effectively enhance HRL agents based on the option-critic architecture. Evaluated in standard environments, a hybrid HRL agent with a quantum feature extractor outperforms classical baselines while using fewer parameters. We also identify an architectural bottleneck: using VQCs for option-value estimation severely degrades learning. Further ablations reveal how quantum circuit design affects performance. Our work establishes design principles for parameter-efficient hybrid HRL agents.

Chemotherapy dose optimization can be formulated as a dynamic treatment regime, requiring sequential decisions under uncertainty that must balance tumor suppression against toxicity. However, most reinforcement learning approaches assume full observability of the patient state, a condition rarely met in clinical practice. We investigate whether memory-augmented policies can improve chemotherapy control under partial observability. To this end, we employ a recurrent TD3-based approach with separate LSTM actor-critic networks and evaluate it on the AhnChemoEnv benchmark from DTR-Bench, considering both off-policy and on-policy recurrent architectures against feed-forward TD3 and Soft Actor-Critic. Pharmacokinetic and pharmacodynamic variability are held fixed to isolate hidden-state uncertainty and observation noise and to avoid confounding effects from inter-patient variability. Across ten random seeds, recurrence yields modest benefit under full observability but substantially stronger and more stable performance under partial observability, with more consistent tumor suppression and improved normal-cell preservation. These findings indicate that memory-based policies are particularly beneficial when clinically relevant state information is incomplete or noisy.

Offline reinforcement learning (RL) can fail spectacularly when bootstrapped temporal-difference (TD) updates amplify their own errors, driving the critic toward extreme and unusable Q-values. A key counterintuitive insight of this work is that collapse is not only a property of the backup rule or network architecture: optimizer dynamics themselves can directly trigger or suppress instability. From a control-theoretic viewpoint, we model offline TD learning as a feedback system and analyze Adam-based critic updates. This yields a necessary and sufficient condition for stability of the induced local update dynamics: within the regime we analyze, these dynamics are stable if and only if the spectral radius of the corresponding update operator is strictly below one. Further analysis suggests that standard Adam updates can inadvertently distort the parameter geometry, motivating explicit orthogonality constraints to prevent TD error amplification. To this end, we propose AdamO, an Adam-based optimizer with a decoupled orthogonality correction regulated by a strict task-alignment budget. We prove that this design theoretically guarantees worst-case task safety and preserves Adam's continuous-time dissipative dynamics. Empirically, AdamO is broadly compatible with diverse offline RL baselines, improving stability and returns across a broad suite of benchmarks.

Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL algorithms achieve favorable sample complexity, but often rely on computationally intractable oracles. In this paper, we use supervised learning as a computational proxy to establish a clear hierarchy of commonly adopted RL oracles under low-rank Markov Decision Processes (MDPs). This hierarchy shows that policy evaluation is the most computationally efficient oracle, provided that supervised learning can be efficiently solved. Motivated by this observation, we propose a novel optimistic actor-critic algorithm that relies solely on the policy evaluation oracle. We prove that our algorithm outperforms the existing sample complexity guarantees for low-rank MDPs while avoiding computationally expensive planning or optimization oracles commonly assumed in prior works. We further extend our theoretical results to approximately low-rank MDPs and demonstrate that this setting captures a broad class of real-world environments. Finally, we validate our theoretical results with experiments on several standard Gym environments.

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities and generalization in embodied manipulation. However, their decision-making relies on a fast, instinctive process that lacks deliberation. This strategy often leads to suboptimal or catastrophic actions when facing complex or ambiguous scenarios that require greater consideration. In this paper, we introduce \textbf{VLA-ATTC}, a framework that endows VLA models with adaptive test-time compute (TTC). VLA-ATTC employs an uncertainty-based ``cognitive clutch'' to dynamically transition from reflexive execution to a TTC deliberation phase when necessary. During TTC phase, a novel \textbf{Relative Action Critic} (RAC) model identifies the optimal action from generated candidates via pairwise comparisons. This relative mechanism replaces unstable absolute value estimation, significantly simplifying the learning objective. Furthermore, we introduce an efficient sampling strategy to amortize computational costs and an automated data pipeline that curates preference pairs without manual annotation. On the LIBERO-LONG benchmark, VLA-ATTC reduces the failure rate of the SOTA model PI0.5 by over 50%. We will open-source all the code and weights.

Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-tests binary reward can be sparse, yielding no learning signal on challenging problems where none of the sampled solutions passes all tests. A common remedy is to use the test-case pass rate as a surrogate reward. In this work, we study pass-rate rewards in critic-free RL for code generation (e.g., GRPO and RLOO) and report a consistent pattern across base models and algorithms: despite alleviating reward sparsity, pass-rate rewards do not reliably improve final performance over binary rewards in rigorous controlled experiments. To understand this discrepancy, we analyze reward density and the resulting gradient directions. We find that pass-rate rewards are denser, but the induced gradient updates do not consistently move probability mass toward full-pass solutions. This arises because test-case pass rate is a miscalibrated surrogate for progress toward full correctness, and partial-pass solutions within the same group can induce conflicting gradient directions that cancel out. Overall, our results suggest that, in critic-free RL, pass-rate rewards are insufficient to improve code generation and motivate reward designs that better align optimization with the goal of full correctness.

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which tend to have high variance, requiring many samples and resulting in slow convergence. We first propose a Bayesian framework for policy gradient, based on modeling the policy gradient as a Gaussian process. This reduces the number of samples needed to obtain accurate gradient estimates. Moreover, estimates of the natural gradient and a measure of the uncertainty in the gradient estimates, namely, the gradient covariance, are provided at little extra cost. Since the proposed framework considers system trajectories as its basic observable unit, it does not require the dynamics within trajectories to be of any particular form, and can be extended to partially observable problems. On the downside, it cannot exploit the Markov property when the system is Markovian. To address this, we supplement our Bayesian policy gradient framework with a new actor-critic learning model in which a Bayesian class of non-parametric critics, based on Gaussian process temporal difference learning, is used. Such critics model the action-value function as a Gaussian process, allowing Bayes rule to be used to compute the posterior distribution over action-value functions, conditioned on the observed data. Appropriate choices of the policy parameterization and of the prior covariance (kernel) between action-values yield closed-form expressions for the posterior of the gradient of the expected return with respect to the policy parameters. We perform detailed experimental comparisons of the proposed Bayesian policy gradient and actor-critic algorithms with classic Monte-Carlo based policy gradient methods, on a number of reinforcement learning problems.

This paper is a continuation work of Ren et al. (2026) aiming to further devise q-learning algorithms for mean-field control (MFC) with controlled common noise. Based on the relaxed control formulation, we first establish the martingale condition of the value function and the Iq-function by evaluating along the conditional state distributions generated by all test policies. As the data in the relaxed control formulation are not observable in practice, we quantify the error incurred when they are replaced by the observable ones in the exploratory formulation under discretely sampled actions. This, together with a two-layer fixed point characterization of an optimal policy in Ren et al. (2026), allows us to propose several algorithms including the Actor-Critic q-learning algorithm, in which the policy is updated in the Actor-step based on the iteration rule induced by the improved Iq-function, and the value function and Iq-function are updated in the Critic-step based on the martingale orthogonality condition using the data from the exploratory formulation. We also establish the convergence of the inner iterations in the Actor-step in an infinite-horizon linear quadratic (LQ) framework. In two examples, within and beyond LQ framework, our q-learning algorithms are implemented with satisfactory performance.

Recent advances in vision language action (VLA) models have shown remarkable potential for autonomous driving by directly mapping multimodal inputs to control signals. However, previous VLA-based methods have not explicitly exploited the critic capability of VLAs to refine driving decisions, even though such capability has been well demonstrated in other LLM-based domains, thereby limiting their performance in complex closed-loop scenarios. In this work, we present a theoretically inspired two-stage framework, CriticVLA, which extends the role of VLAs from acting to judging. CriticVLA first generates a rough trajectory and then refines it through multimodal evaluation and single-step optimization guided by a VLA-based critic, yielding higher-quality driving behaviors. To support this process, we construct a large-scale synthetic dataset of 12.9 million annotated trajectories covering diverse driving scenarios, which enhances the critic's reasoning and refinement abilities. Extensive closed-loop experiments on the Bench2Drive benchmark show that CriticVLA significantly surpasses state-of-the-art baselines, achieving a 73.33% total success rate and delivering about 30% improvement in challenging scenarios.

This paper explores the application of the Soft Actor-Critic (SAC) algorithm within a Distributional Reinforcement Learning setting and introduces an implementation of such algorithm named Cramér-based Distributional Soft Actor-Critic (C-DSAC). The novel approach employs distributional reinforcement learning to represent state-action values, and minimizes the squared Cramér distance for learning the distribution. Empirical results across various robotic benchmarks indicate that our algorithm surpasses the performance of baseline SAC and contemporary distributional methods, with the performance advantage becoming increasingly pronounced in high-complexity environments. To explain the efficiency of the new approach, we conduct an analysis showing that its superior performance is partly due to \textit{confidence-driven} Q-value updates: High-variance target distributions (low confidence in target) lead to more conservative model updates, thereby attenuating the impact of overestimated values. This work deepens the understanding of distributional reinforcement learning, offering insights into the algorithmic mechanisms governing convergence and value estimation.

Due to the textual and repetitive nature of many Requirements Engineering (RE) artefacts, Large Language Models (LLMs) have proven useful to automate their generation and processing. In this paper, we discuss a possible approach for automating the Goal-Oriented Requirements Engineering (GORE) process by extracting functional goals from software documentation through three phases: actor identification, high and low-level goal extraction. To implement these functionalities, we propose a chain of LLMs fed with engineered prompts. We experimented with different variants of in-context learning and measured the similarities between input data and in-context examples to better investigate their impact. Another key element is the generation-critic mechanism, implemented as a feedback loop involving two LLMs. Although the pipeline achieved 61% accuracy in low-level goal identification, the final stage, these results indicate the approach is best suited as a tool to accelerate manual extraction rather than as a full replacement. The feedback-loop mechanism with Zero-shot outperformed stand-alone Few-shot, with an ablation study suggesting that performance slightly degrades without the feedback cycle. However, we reported that the combination of the feedback mechanism with Few-shot does not deliver any advantage, possibly suggesting that the primary performance ceiling is the prompting strategy applied to the 'critic' LLM. Together with the refinement of both the quantity and quality of the Shot examples, future research will integrate Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) prompting to improve accuracy.

Graphical User Interface (GUI) grounding requires mapping natural language instructions to precise pixel coordinates. However, due to visually homogeneous elements and dense layouts, models typically grasp semantic intent yet struggle with achieving precise localization. While scaling sampling attempts (Pass@k) reveals potential gains, static self-consistency strategies derived from geometric clustering often yield limited improvements, as the model's predictions tend to be spatially dispersed. In this paper, we propose replacing static consistency strategies with a learnable selection mechanism that selects the optimal target by critiquing its own proposals rendered on the screenshot. Given the significant disparity between the model's grounding and critiquing capabilities, we propose a co-evolving Propose-then-Critic framework. To jointly optimize these, we introduce a maturity-aware adaptive co-evolutionary reinforcement learning paradigm. This approach dynamically balances the training objectives of proposer and critic, where the diversity of the proposer's outputs enhances critic robustness, while the critic's maturing discrimination capability conversely unlocks the proposer's potential for extensive spatial exploration, fostering the mutual reinforcement and co-evolution of both capabilities, thereby ensuring generalizability to adapt to diverse and complex interface layouts. Extensive experiments over 6 benchmarks show that our method significantly enhances both grounding accuracy and critic reliability.

Quality-Diversity (QD) algorithms excel at discovering diverse repertoires of skills, but are hindered by poor sample efficiency and often require tens of millions of environment steps to solve complex locomotion tasks. Recent advances in Reinforcement Learning (RL) have shown that high Update-to-Data (UTD) ratios accelerate Actor-Critic learning. While effective, standard high-UTD algorithms typically utilise target networks to stabilise training. This requirement introduces a significant computational bottleneck, rendering them impractical for resource-intensive Quality-Diversity (QD) tasks where sample efficiency and rapid population adaptation are critical. In this paper, we introduce QDHUAC, a sample-efficient, target-free and distributional QD-RL algorithm that provides dense and low-variance gradient signals, which enables high-UTD training for Dominated Novelty Search whilst requiring an order of magnitude fewer environment steps. We demonstrate that our method enables stable training at high UTD ratios, achieving competitive coverage and fitness on high-dimensional Brax environments with an order of magnitude fewer samples than baselines. Our results suggest that combining target-free distributional critics with dominance-based selection is a key enabler for the next generation of sample-efficient evolutionary RL algorithms.

While Central Pattern Generators (CPGs) and Multi-Layer Perceptrons (MLP) are widely used paradigms in robot control, few systematic studies have been performed on the relative merits of large parameter spaces. In contexts where input and output spaces are small and performance is bounded, having more parameters to optimize may actively hinder the learning process instead of empowering it. To empirically measure this, we submit a given robot morphology, with limited proprioceptive capabilities, to controller optimization under two bio-inspired paradigms (CPGs and MLPs) with evolutionary- and reinforcement- trainer protocols. By varying parameter spaces across multiple reward functions, we observe that shallow MLPs and densely connected CPGs result in better performance when compared to deeper MLPs or Actor-Critic architectures. To account for the relationship between said performance and the number of parameters, we introduce a Parameter Impact metric which demonstrates that the additional parameters required by the reinforcement technique do not translate into better performance, thus favouring evolutionary strategies.

Mixture-of-Experts models, now popular for scaling capacity at fixed inference speed, switch experts at nearly every token. Once a model outgrows available GPU memory, this churn can render optimizations like offloading and pre-fetching ineffective. We make the case that the options framework in reinforcement learning is a perfect match to tackle this problem, and argue for temporally extended mixture-of-experts layers. Building on the option-critic framework with deliberation costs, we add a controller to each layer that learns when to switch expert sets and which to load. By applying this to gpt-oss-20b with low-rank adapters and a self-distillation reward, our method reduces switch rates from over 50% to below 5% while retaining up to 90% of base-model accuracy on MATH, MMLU, and MMMLU. This shows that even existing pre-trained models can be converted to temporally extended MoEs with lightweight training, with the deliberation cost allowing model trainers to trade off switching rates against capability. We hope this opens a principled path, grounded in the options framework, for memory-efficient serving and continual learning in ever-growing MoE models.

Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and instability in replay-based bootstrapped training. In this paper, we propose using Low-Rank Adaptation (LoRA) as a structural regularizer for critic learning. Our approach freezes randomly initialized base matrices and optimizes only the corresponding low-rank adapters, thereby constraining critic updates to a low-dimensional subspace. We evaluate our method across different off-policy RL algorithms, including SAC and FastTD3 based on different network architectures. Empirically, LoRA efficiently reduces critic loss during training and improves overall policy performance, achieving the best or competitive results on most tasks. Extensive experiments demonstrate that our low-rank updates provide a simple and effective form of structural regularization for critic learning in off-policy RL.

We propose MADDPG-K, a scalable extension to Multi-Agent Deep Deterministic Policy Gradient (MADDPG) that addresses the computational limitations of centralized critic approaches. Centralized critics, which condition on the observations and actions of all agents, have demonstrated significant performance gains in cooperative and competitive multi-agent settings. However, their critic networks grow linearly in input size with the number of agents, making them increasingly expensive to train at scale. MADDPG-K mitigates this by restricting each agent's critic to the $k$ closest agents under a chosen metric which in our case is Euclidean distance. This ensures a constant-size critic input regardless of the total agent count. We analyze the complexity of this approach, showing that the quadratic cost it retains arises from cheap scalar distance computations rather than the expensive neural network matrix multiplications that bottleneck standard MADDPG. We validate our method empirically across cooperative and adversarial environments from the Multi-Particle Environment suite, demonstrating competitive or superior performance compared to MADDPG, faster convergence in cooperative settings, and better runtime scaling as the number of agents grows. Our code is available at https://github.com/TimGop/MADDPG-K .

In cooperative teams where agents act in a fixed order and share a single team-level reward (multi-agent language systems, sequential robotic tasks), per-agent credit assignment is under-determined. Critic-based approaches scale poorly as the number of agents grows owing to the costly maintenance of joint/factored critic(s), whereas the existing critic-free alternatives have other issues: common credit across agents that couples every agent's signal to teammate noise, importance-sampling corrections for upstream-update staleness that incur variance exponential in team size, or per-agent counterfactual replay that isolates each agent's effect at the price of extra environment or reward calls. We propose COSAC, a critic-free per-agent policy gradient for sequential cooperative teams. COSAC fits an additive per-agent decomposition of the team reward by a single ridge regression on the rollout batch (giving each agent a learning signal decoupled from teammate noise), and computes each agent's counterfactual advantage from fictitious continuations of the current policy (policy forward passes that replace both importance-sampling reweighting and per-agent environment replay, at no extra environment or reward cost). The estimator instantiates the Sequential Aristocrat Utility (SeqAU), our extension of Wolpert and Tumer's (2001) aristocrat utility to sequential teams. We prove bias and variance bounds on SeqAU credits that stay controlled as the team grows. Our controlled study on sequential bandits demonstrates that COSAC attains the lowest advantage MSE and consistently low learning regret across team sizes up to $K = 16$. On the AI2 Reasoning Challenge (ARC) task, where four Qwen3-0.6B agents reason in turn about a grade-school science question, COSAC attains faster convergence than the other critic-free baselines.

Accurate process supervision remains a critical challenge for long-horizon robotic manipulation. A primary bottleneck is that current video MLLMs, trained primarily under a Supervised Fine-Tuning (SFT) paradigm, function as passive "Observers" that recognize ongoing events rather than evaluating the current state relative to the final task goal. In this paper, we introduce PRIMO R1 (Process Reasoning Induced Monitoring), a 7B framework that transforms video MLLMs into active "Critics". We leverage outcome-based Reinforcement Learning to incentivize explicit Chain-of-Thought generation for progress estimation. Furthermore, our architecture constructs a structured temporal input by explicitly anchoring the video sequence between initial and current state images. Supported by the proposed PRIMO Dataset and Benchmark, extensive experiments across diverse in-domain environments and out-of-domain real-world humanoid scenarios demonstrate that PRIMO R1 achieves state-of-the-art performance. Quantitatively, our 7B model achieves a 50% reduction in the mean absolute error of specialized reasoning baselines, demonstrating significant relative accuracy improvements over 72B-scale general MLLMs. Furthermore, PRIMO R1 exhibits strong zero-shot generalization on difficult failure detection tasks. We establish state-of-the-art performance on RoboFail benchmark with 67.0% accuracy, surpassing closed-source models like OpenAI o1 by 6.0%.

On-policy Reinforcement Learning (RL) remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy, and policy updates must be conservative. In this paper, we revisit actor policy representation as a first-class design choice for on-policy RL. We study discretized categorical actors, which represent each action dimension as a distribution over discrete bins and induce a policy objective analogous to classification cross-entropy loss. Building on architectural advances from supervised learning, we further pair discretized categorical actors with regularized networks, yielding RN-D. Across diverse continuous-control benchmarks, we show that simply replacing the standard Gaussian actor with our proposed actor substantially improves performance, achieving state-of-the-art results within on-policy RL. We release our code at https://github.com/alwaysbyx/RND-RL.

While Large Vision-Language Models (LVLMs) have significantly advanced GUI agents' capabilities in parsing textual instructions, interpreting screen content, and executing tasks, a critical challenge persists: the irreversibility of agent operations-where a single erroneous action can trigger catastrophic deviations. To address this, we propose the \textbf{G}UI \textbf{A}ction Cr\textbf{i}tic's Dat\textbf{a} Flywheel System (GAIA), a training framework that enables the models to have iterative critic capabilities, which are used to improve the Test-Time Scaling (TTS) of basic GUI agents' performance. Specifically, we train an \textbf{Intuitive Critic Model} (ICM) using positive and negative action examples from a base agent first. This critic evaluates the immediate correctness of the agent's intended actions, thereby selecting operations with higher success probability. Then, the initial critic guides agent actions to collect refined positive/negative samples, initiating the self-improving cycle. The augmented data then trains a second-round critic with enhanced discernment capability. We conduct experiments on various datasets and demonstrate that the proposed ICM can improve the test-time performance of various closed-source and open-source models, and the performance can be gradually improved as the data is recycled. The code, dataset, and accompanying datasheet will be publicly released at https://github.com/SeerRay-Lab/GAIA.

Reinforcement learning has enabled impressive locomotion skills on articulated robots, but common policy representations remain only weakly aligned with robot physics. Generic networks ignore kinematic structure, while graph-based policies encode connectivity without specifying how physical quantities transform across symmetric body parts. We introduce a morphological symmetry graph representation for locomotion policy learning and instantiate it in MS-PPO. Starting from the robot's topological graph, our representation augments each observation and action space with the permutation and sign transformations induced by morphological symmetry. This yields a symmetry-equivariant graph actor and a symmetry-invariant graph critic, enforcing the desired policy and value constraints by construction rather than through reward shaping or data augmentation. We evaluate MS-PPO on a variety of locomotion tasks using both Unitree Go2 quadruped and Unitree G1 humanoid, including command tracking, asymmetric joint failures, out-of-distribution command generalization, and zero-shot sim-to-real deployment. Experiments show improved symmetry generalization, robustness, sample efficiency, and model efficiency over topology- and symmetry-aware baselines.

Text-to-3D generation has advanced rapidly, yet state-of-the-art models, encompassing both optimization-based and feed-forward architectures, still face two fundamental limitations. First, they struggle with coarse semantic alignment, often failing to capture fine-grained prompt details. Second, they lack robust 3D spatial understanding, leading to geometric inconsistencies and catastrophic failures in part assembly and spatial relationships. To address these challenges, we propose VLM3D, a general framework that repurposes large vision-language models (VLMs) as powerful, differentiable semantic and spatial critics. Our core contribution is a dual-query critic signal derived from the VLM's Yes or No log-odds, which assesses both semantic fidelity and geometric coherence. We demonstrate the generality of this guidance signal across two distinct paradigms: (1) As a reward objective for optimization-based pipelines, VLM3D significantly outperforms existing methods on standard benchmarks. (2) As a test-time guidance module for feed-forward pipelines, it actively steers the iterative sampling process of SOTA native 3D models to correct severe spatial errors. VLM3D establishes a principled and generalizable path to inject the VLM's rich, language-grounded understanding of both semantics and space into diverse 3D generative pipelines.

Multi-agent reinforcement learning (MARL) has shown promise for large-scale network control, yet existing methods face two major limitations. First, they typically rely on an exponential decay property of agent interactions on far-away nodes, which can be exploited to develop more efficient and tractable MARL algorithms. When this exponential decay property does not hold, these algorithms do not account for long-range interactions such as epidemic outbreaks or cascading power failures. Second, existing approaches lack network generalizability, or the ability to generalize to networks of different topological structure and scale than those seen during training. In this work, we first present a mean-field stability analysis and empirical study investigating the conditions for long-range network interactions. These results motivate our primary contribution: STACCA (Shared Transformer Actor-Critic with Counterfactual Advantage), a transformer-based MARL framework that addresses both long-range interactions and network generalizability. STACCA employs a centralized Graph Transformer Critic to model long-range dependencies and provide system-level feedback, while its shared Graph Transformer Actor learns a generalizable policy capable of adapting across diverse network topologies. To improve credit assignment during training, STACCA integrates a novel counterfactual advantage estimator that is compatible with state-value critic estimates. We evaluate STACCA on epidemic containment and rumor-spreading network control tasks, demonstrating improved performance and network generalizability. These results highlight the potential of transformer-based MARL architectures to achieve generalizable control in large-scale networked systems.

The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot locomotion, individual skills are often learned from scratch despite the high likelihood that some generalizable knowledge is shared across all task-specific policies belonging to the same robot embodiment. This work aims to define a paradigm for pretraining neural network models that encapsulate such knowledge and can subsequently serve as a basis for warm-starting the RL process in classic actor-critic algorithms, such as Proximal Policy Optimization (PPO). We begin with a task-agnostic exploration-based data collection algorithm to gather diverse, dynamic transition data, which is then used to train a Proprioceptive Inverse Dynamics Model (PIDM) through supervised learning. The pretrained weights are then loaded into both the actor and critic networks to warm-start the policy optimization of actual tasks. We systematically validated our proposed method with 9 distinct robot locomotion RL environments comprising 3 different robot embodiments, showing significant benefits of this initialization strategy. Our proposed approach on average improves sample efficiency by 36.2% and task performance by 4.3% compared to random initialization. We further present key ablation studies and empirical analyses that shed light on the mechanisms behind the effectiveness of this method.

Humanoid robots are promising to acquire various skills by imitating human behaviors. However, existing algorithms are only capable of tracking smooth, low-speed human motions, even with delicate reward and curriculum design. This paper presents a physics-based humanoid control framework, aiming to master highly-dynamic human behaviors such as Kungfu and dancing through multi-steps motion processing and adaptive motion tracking. For motion processing, we design a pipeline to extract, filter out, correct, and retarget motions, while ensuring compliance with physical constraints to the maximum extent. For motion imitation, we formulate a bi-level optimization problem to dynamically adjust the tracking accuracy tolerance based on the current tracking error, creating an adaptive curriculum mechanism. We further construct an asymmetric actor-critic framework for policy training. In experiments, we train whole-body control policies to imitate a set of highly-dynamic motions. Our method achieves significantly lower tracking errors than existing approaches and is successfully deployed on the Unitree G1 robot, demonstrating stable and expressive behaviors. The project page is https://kungfubot.github.io.

We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs). We present non-asymptotic convergence analyses of Q-learning and actor-critic algorithms for robust average-reward MDPs under contamination, total-variation distance, and Wasserstein uncertainty sets. A key ingredient of our analysis is showing that the optimal robust Bellman operator is a strict contraction with respect to a carefully designed semi-norm. This property enables a stochastic approximation update that learns the optimal robust $Q$-function with $\tilde{\mathcal{O}}(ε^{-2})$ dependence on the target accuracy. We also establish robust TD convergence bounds whose constants are uniform over all stationary policies, yielding an efficient data-driven routine for robust critic estimation. Building on this, we introduce an actor-critic algorithm that learns an $ε$-optimal robust policy with $\tilde{\mathcal{O}}(ε^{-2})$ dependence on the target accuracy. We provide numerical simulations to illustrate the qualitative behavior of the proposed algorithms. Our results contribute to the theoretical foundations of robust planning under model misspecification and to model-free approaches for building robust long-run policies directly from simulation data.

Constrained Reinforcement Learning (RL) has emerged as a significant research area within RL, where integrating constraints with rewards is crucial for enhancing safety and performance across diverse control tasks. In the context of heating systems in the buildings, optimizing the energy efficiency while maintaining the residents' thermal comfort can be intuitively formulated as a constrained optimization problem. However, to solve it with RL may require large amount of data. Therefore, an accurate and versatile simulator is favored. In this paper, we propose a novel building simulator I4B which provides interfaces for different usages and apply a model-free constrained RL algorithm named constrained Soft Actor-Critic with Linear Smoothed Log Barrier function (CSAC-LB) to the heating optimization problem. Benchmarking against baseline algorithms demonstrates CSAC-LB's efficiency in data exploration, constraint satisfaction and performance.

Regularization is a cornerstone of modern reinforcement learning. Regularized policy iteration (RPI) provides a fundamental scheme for solving regularized Markov decision processes (RMDPs), and the widely used soft actor-critic algorithm arises as a special case when the regularizer is Shannon entropy. Despite its empirical success, the theoretical underpinnings of RPI remain unclear. In this paper, we address this gap by proving that RPI is formally equivalent to the standard Newton-Raphson method applied to the Bellman equation smoothed by strongly convex regularizers. This equivalence enables a unified convergence analysis of existing methods and supports the development of accelerated algorithms. We show that RPI enjoys local quadratic convergence; notably, for Shannon entropy, the guarantee is dimension-free. We further study RPI with inexact policy evaluation, establishing its equivalence to an inexact Newton method in which each Newton step is solved via truncated iterations, and derive an asymptotic linear convergence rate of $γ^{M}$, where $M$ denotes the number of operator steps used in policy evaluation. Finally, motivated by higher-order Newton schemes, we propose a new algorithm for RMDPs that achieves third-order local convergence. Numerical experiments corroborate our theory and demonstrate the practical advantages of the proposed algorithm. Overall, our results advance the theoretical understanding of regularization in reinforcement learning and suggest new directions for efficient algorithm design.

We study formal policy synthesis for continuous-state stochastic systems under linear temporal logic specifications. The product of the system with the automaton of the specification has a hybrid state space with sparse rewards. We introduce a generalized optimal backup order, defined in reverse to a topological order over automaton states, that guides value backups and provably preserves optimality. We further present a model-free actor-critic algorithm whose policy evaluation solves a constrained optimization problem by the augmented Lagrangian method, yielding hyperparameter self-tuning, and prove its optimality and convergence in the tabular case. Since integer encodings of automaton states impose a spurious ordinal relationship on functions learned by one network, we dedicate a value and a policy network to each automaton state (modular learning). The algorithm matches or outperforms PPO, DQN, and A2C on CartPole, and on a Dubins car under a temporal specification the topological order and modular learning raise the success rate from 26.0% to 71.5%.

Temporal abstraction allows reinforcement learning agents to represent knowledge and develop strategies over different temporal scales. The option-critic framework has been demonstrated to learn temporally extended actions, represented as options, end-to-end in a model-free setting. However, feasibility of option-critic remains limited due to two major challenges, multiple options adopting very similar behavior, or a shrinking set of task relevant options. These occurrences not only void the need for temporal abstraction, they also affect performance. In this paper, we tackle these problems by learning a diverse set of options. We introduce an information-theoretic intrinsic reward, which augments the task reward, as well as a novel termination objective, in order to encourage behavioral diversity in the option set. We show empirically that our proposed method is capable of learning options end-to-end on several discrete and continuous control tasks, outperforms option-critic by a wide margin. Furthermore, we show that our approach sustainably generates robust, reusable, reliable and interpretable options, in contrast to option-critic.

Credit assignment is a central challenge in reinforcement learning (RL). Classical actor-critic methods address this challenge through fine-grained advantage estimation based on a learned value function. However, learned value models are often avoided in modern large language model (LLM) RL because conventional discriminative critics are difficult to train reliably. We revisit value modeling and argue that this difficulty is partly due to limited expressiveness. In particular, representation complexity theory suggests that value functions can be hard to approximate under the one-shot prediction paradigm used by existing value models, and our scaling experiments show that such critics do not improve reliably with scale. Motivated by this observation, we propose Generative Actor-Critic (GenAC), which replaces one-shot scalar value prediction with a generative critic that performs chain-of-thought reasoning before producing a value estimate. We further introduce In-Context Conditioning, which helps the critic remain calibrated to the current actor throughout training. GenAC improves value approximation, ranking reliability, and out-of-distribution generalization, and these gains translate into stronger downstream RL performance than both value-based and value-free baselines. Overall, our results suggest that stronger value modeling is a promising direction for improving credit assignment in LLM reinforcement learning.