Reinforcement Learning

Also known as RL

Follow this topic Ask about this topic

Momentum

144 papers in the last four weeks, up 243% on the four weeks before. 1.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 1,138

May 14, 2026cs.LG

Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients

We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index) and the continuous component optimizes within it -- a structure common in robotics, control, and operations problems. Standard model-free policy gradient methods rely on score-function (SF) estimators and suffer from severe credit-assignment issues in high-dimensional settings, leading to poor gradient quality. On the other hand, differentiable simulation largely sidesteps these issues by backpropagating through a simulator, but the presence of discrete actions or non-smooth dynamics yields biased or uninformative gradients. To address this, we propose Hybrid Policy Optimization (HPO), which backpropagates through the simulator wherever smoothness permits, using a mixed gradient estimator that combines pathwise and SF gradients while maintaining unbiasedness. We also show how problems with action discontinuities can be reformulated in hybrid form, further broadening its applicability. Empirically, HPO substantially outperforms PPO on inventory control and switched linear-quadratic regulator problems, with performance gaps increasing as the continuous action dimension grows. Finally, we characterize the structure of the mixed gradient, showing that its cross term -- which captures how continuous actions influence future discrete decisions -- becomes negligible near a discrete best response, thereby enabling approximate decentralized updates of the continuous and discrete components and reducing variance near optimality. All resources are available at github.com/MatiasAlvo/hybrid-rl.

Matias Alvo, Daniel Russo, Yash Kanoria

Graduate School of Business Columbia University

RL Control Reinforcement Learning Policy Optimization

May 14, 2026cs.CV

CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL

Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training offers a natural route to adapting VGMs, existing video-RL rewards often reduce each rollout to a low-level visual metric, whereas manipulation video evaluation requires logic-based verification of whether the rollout satisfies a compositional task specification. To fill this gap, we introduce a compositional constraint-based reward model for post-training embodied video generation models, which automatically formulates task requirements as a composition of Linear Temporal Logic constraints, providing faithful rewards and localized error information in generated videos. To achieve effective improvement in high-dimensional video generation using these reward signals, we further propose CreFlow, a novel online RL framework with two key designs: i) a credit-aware NFT loss that confines the RL update to reward-relevant regions, preventing perturbations to unrelated regions during post-training; and ii) a corrective reflow loss that leverages within-group positive samples as an explicit estimate of the correction direction, stabilizing and accelerating training. Experiments show that CreFlow yields reward judgments better aligned with human and simulator success labels than existing methods and improves downstream execution success by 23.8 percentage points across eight bimanual manipulation tasks.

Zhenyang Ni, Yijiang Li, Ruochen Jiao +7

Northwestern University · University of California, San Diego · University of Oxford

Video Diffusion Models Reinforcement Learning RL for Video Generation Constrained RL RL for Diffusion Models RL for Generative Models+1

May 14, 2026cs.LG

Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference

Modern LLM RL systems separate rollout generation from policy optimization. These two stages are expected to produce token probabilities that match exactly. However, implementation differences can make them assign different values to the same sequence under the same model weights, inducing Training-Inference Mismatch (TIM). TIM is difficult to inspect because it is entangled with off-policy drift and common stabilization mechanisms. In this work, we isolate TIM in a zero-mismatch diagnostic setting (VeXact), and show that small token-level numerical disagreements can independently cause training collapse. We further show that TIM changes the effective optimization problem, and identify a set of remedies that could mitigate TIM. Our results suggest that TIM is not benign numerical noise, but a systems-level perturbation that should be treated as a first-order factor in analyzing LLM RL stability.

Tianle Zhong, Neiwen Ling, Yifan Pi +5

ByteDance · The University of Virginia

Reinforcement Learning LLM Inference RL Post-Training

May 13, 2026cs.LG

R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning

For reinforcement learning in data-scarce domains like real-world robotics, intensive data reuse enhances efficiency but induces overfitting. While prior works focus on critic bias, representation-level instability in Self-Predictive Learning (SPL) under high Update-to-Data (UTD) regimes remains underexplored. To bridge this gap, we propose Robust Representation via Redundancy Reduction (R2R2), a regularization method within SPL. We theoretically identify that standard zero-centering conflicts with SPL's spectral properties and design a non-centered objective accordingly. We verify R2R2 on SPL-native algorithms like TD7. Furthermore, to demonstrate its orthogonality to prior advancements, we extend the state-of-the-art SimbaV2, which originally lacks SPL, by integrating a tailored SPL module, termed SimbaV2-SPL. Experiments across 11 continuous control tasks confirm that R2R2 effectively mitigates overfitting; specifically, at a UTD ratio of 20, it improves TD7 by ~22% and provides additional gains on top of SimbaV2-SPL, which itself establishes a new state-of-the-art. The code can be found at: https://github.com/songsang7/R2R2

Sanghyeob Song, Donghyeok Lee, Jinsik Kim +1

Interdisciplinary Program in Artificial Intelligence, Seoul National University · Samsung Electro-Mechanics, Republic of Korea · Department of Electrical and Computer Engineering, Seoul National University

Reinforcement Learning Self-Supervised Learning Representation Learning for RL Robust RL Sample-Efficient RL

May 13, 2026cs.LG

Tight Sample Complexity Bounds for Entropic Best Policy Identification

We study best-policy identification for finite-horizon risk-sensitive reinforcement learning under the entropic risk measure. Recent work established a constant gap in the exponential horizon dependence between lower and upper bounds on the number of samples required to identify an approximately optimal policy. Precisely, known lower bounds scale in

Ω(e^{|β| H})

where

H

is the horizon of the MDP, while the state-of-the-art upper bound achieves at best

O(e^{2|β| H})

(arXiv:2506.00286v2) using a generative model. We show that this extra exponential factor can be traced to overly loose concentration control for exponential utilities. To close this open gap, we revisit the analysis of this problem through a forward-model based algorithm building on KL-based exploration bonuses that we adapt to the entropic criterion. The improvement we get is due to two main novel technical innovations. We leverage the smoothness properties of the exponential utility to derive sharper concentration bounds, and we propose a new stopping rule that exploits further this tightness to obtain a sample complexity that matches the lower bound.

Amer Essakine, Claire Vernade

ENS Paris Saclay · University of Technology Nuremberg

Reinforcement Learning Risk-Sensitive RL Policy Learning Sample-Efficient RL

May 13, 2026cs.LG

Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation

Contrastive reinforcement learning (CRL) learns goal-conditioned Q-values through a contrastive objective over state-action and goal representations, removing the need for hand-crafted reward functions. Despite impressive success in achieving viable self-supervised learning in RL, all existing CRL algorithms rely on off-policy optimisation and are mostly constrained to continuous action spaces, with little research invested in discrete environments. This leaves CRL disconnected from widely used and effective, modern on-policy training pipelines adopted across both single-agent and multi-agent RL in continuous and discrete environments. To establish a first connection, we introduce Contrastive Proximal Policy Optimisation (CPPO). CPPO is an on-policy contrastive RL algorithm that derives policy advantages directly from contrastive Q-values and optimises them via the standard PPO objective, without requiring a reward function or a replay buffer. We evaluate CPPO across continuous and discrete, single-agent and cooperative multi-agent tasks. Whilst the existence of an on-policy approach is inherently useful, we observe that \textbf{CPPO not only significantly outperforms the previous CRL baselines in 14 out of 18 tasks, but also matches or exceeds PPO's performance, which uses hand-crafted dense rewards, in 12 out of the 18 tasks tested.}

Asim Osman, Sasha Abramowitz, Mark Bergh +13

InstaDeep, AIMS · InstaDeep, University of Stellenbosch

Reinforcement Learning Contrastive RL Goal-Conditioned RL

May 13, 2026cs.SE

CA2: Code-Aware Agent for Automated Game Testing

Automated game testing is important for verifying game functionality, but it remains a costly and time-consuming process. Manual testing often misses edge cases, and current automated methods struggle to provide full code coverage. Prior work has explored reinforcement learning (RL) for game testing, but without leveraging internal code signals such as the call stack. We present Code Aware Agent (CA2), which uses call stack information to learn effective testing strategies. The agent receives the current function call trace along with the game state and learns to reach specific target functions. We instrument two types of environments, 1) State-based and 2) Image-based, with support for efficient call stack extraction. Through experimental evaluation, we find that CA2 achieves consistent improvement over the non-code aware baselines, which does not leverage call stack information. Our results show that incorporating code signals like the call stack enables more effective and targeted game testing.

Valliappan Chidambaram Adaikkappan, Vincent Martineau, Joshua Romoff +1

† McGill University · ⋄Mila Quebec AI Institute · ‡ Ubisoft

Automated Software Testing Reinforcement Learning Automated Test Generation

May 13, 2026cs.LG

Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy

There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity. However, effectively leveraging this expressivity for value maximization remains challenging, as naive gradient-based optimization requires backpropagating through numerical solvers and often leads to instability. Existing approaches typically address this issue by restricting the expressive capacity of flow-based policies, resulting in a trade-off between optimization stability and representational flexibility. To resolve this, we introduce Q-Flow, a framework that leverages the deterministic nature of flow dynamics to explicitly propagate terminal trajectory value to intermediate latent states along the policy-induced flow. This formulation enables stable policy optimization using intermediate value gradients without unrolling the numerical solver, effectively bridging the gap between stability and expressivity. We evaluate Q-Flow in the offline learning setting on the challenging OGBench suite, where it consistently outperforms state-of-the-art baselines by an average of 10.6 percentage points, while also enabling stable online adaptation within the same framework.

JaeHyeok Doo, Byeongguk Jeon, Seonghyeon Ye +2

1KAIST

Reinforcement Learning Offline RL

May 13, 2026cs.AI

D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models

The rapid evolution of Embodied AI has enabled Vision-Language-Action (VLA) models to excel in multimodal perception and task execution. However, applying Reinforcement Learning (RL) to these massive models in large-scale distributed environments faces severe systemic bottlenecks, primarily due to the resource conflict between high-fidelity physical simulation and the intensive VRAM/bandwidth demands of deep learning. This conflict often leaves overall throughput constrained by execution-phase inefficiencies. To address these challenges, we propose D-VLA, a high-concurrency, low-latency distributed RL framework for large-scale embodied foundation models. D-VLA introduces "Plane Decoupling," physically isolating high-frequency training data from low-frequency weight control to eliminate interference between simulation and optimization. We further design a four-thread asynchronous "Swimlane" pipeline, enabling full parallel overlap of sampling, inference, gradient computation, and parameter distribution. Additionally, a dual-pool VRAM management model and topology-aware replication resolve memory fragmentation and optimize communication efficiency. Experiments on benchmarks like LIBERO show that D-VLA significantly outperforms mainstream RL frameworks in throughput and sampling efficiency for billion-parameter VLA models. In trillion-parameter scalability tests, our framework maintains exceptional stability and linear speedup, providing a robust system for high-performance general-purpose embodied agents.

Yucheng Guo, Yongjian Guo, Zhong Guan +9

JDT AI Infra · Tsinghua University · Tianjin University +2

Reinforcement Learning Communication-Efficient Distributed Training Vision-Language-Action Models RL for VLMs

May 13, 2026cs.CL

GAGPO: Generalized Advantage Grouped Policy Optimization

Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end of an episode, making it difficult to determine which intermediate actions contributed to success or failure. As a result, propagating delayed outcomes back to individual decision steps without relying on costly auxiliary value models remains an open problem. We propose Generalized Advantage Grouped Policy Optimization (GAGPO), a critic-free reinforcement learning method for precise, step-aligned temporal credit assignment. GAGPO constructs a non-parametric grouped value proxy from sampled rollouts and uses it to compute TD/GAE-style temporal advantages, recursively propagating outcome supervision backward through time. Combined with group-wise advantage normalization and an action-level importance ratio, GAGPO extracts stable, localized optimization signals directly from multi-turn trajectories. Experiments on ALFWorld and WebShop show that GAGPO outperforms strong reinforcement learning baselines. Further analyses demonstrate faster early-stage learning, improved interaction efficiency, and smoother optimization dynamics, suggesting that GAGPO offers a simple yet effective framework for multi-turn agentic reinforcement learning.

Siyuan Zhu, Chao Yu, Rongxin Yang +4

School of Computer Science and Engineering, Sun Yat-sen University · Meituan

Reinforcement Learning Group Relative Policy Optimization Credit Assignment in RL Step-Level Credit Assignment in RL Critic-Free RL Policy Learning+1

May 13, 2026cs.LG

Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning

Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing approaches often rely on restrictive design choices, such as fixed temporal abstractions or goal-conditioned objectives, which largely confine them to goal-reaching tasks and limit their applicability to general reward functions. In this paper, we introduce switching successor measures, an extension of successor measures that enables hierarchical control in zero-shot reinforcement learning without additional supervision, fixed horizons, or manually designed subgoals. We show that switching successor measures arise naturally from classical successor measures while preserving their underlying structure. Building on this result, we propose FB

π

-Switch, an algorithm that extracts both a high-level subgoal-selection policy and a low-level control policy directly from forward-backward (FB) representations, allowing hierarchical behavior to emerge from a single learned representation. Experiments on both goal-conditioned and general reward-based tasks show that FB

π

-Switch improves over non-hierarchical baselines and matches state-of-the-art hierarchical methods in goal-conditioned settings. These results demonstrate that structured successor representations provide a flexible foundation for hierarchical zero-shot reinforcement learning beyond goal-reaching tasks. Our project website is available at: https://stestokth.github.io/switching-successors/.

Stefan Stojanovic, Alexandre Proutiere

KTH, Stockholm, Sweden · KTH, Digital Futures, Stockholm, Sweden

Representation Learning Reinforcement Learning Hierarchical RL Successor Representations

May 13, 2026cs.LG

Offline Two-Player Zero-Sum Markov Games with KL Regularization

We study the problem of learning Nash equilibria in offline two-player zero-sum Markov games. While existing approaches often rely on explicit pessimism to address distribution shift, we show that KL regularization alone suffices to stabilize learning and guarantee convergence. We first introduce Regularized Offline Sequential Equilibrium (ROSE), a theoretical framework that achieves a fast

\widetilde{\mathcal{O}}(1/n)

convergence rate under \textit{unilateral concentrability}, improving over the standard

\widetilde{\mathcal{O}}(1/\sqrt{n})

rates in unregularized settings. We then propose Sequential Offline Self-play Mirror Descent (SOS-MD), a practical model-free algorithm based on least-squares value estimation and iterative self-play updates. We prove that the last iterate of SOS-MD attains the same

\widetilde{\mathcal{O}}(1/n)

statistical rate up to a vanishing optimization error of order

\widetilde{\mathcal{O}}(1/\sqrt{T})

in the number of self-play iterations

T

.

Claire Chen, Yuheng Zhang, Xinyu Liu +3

1California Institute of Technology. · University of Illinois Urbana-Champaign. · University of Virginia. +2

Nash Equilibrium Reinforcement Learning Self-Play RL KL-Regularized RL Game Theory Zero-Sum Games+3

May 13, 2026cs.LG

Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints

Safe reinforcement learning in nonstationary environments requires safety mechanisms that adapt as environmental conditions change. Standard safe reinforcement learning methods often assume fixed constraints or stable environmental conditions, which can become inadequate under distribution shift. We propose LILAC+, a framework for safe continual reinforcement learning under nonstationarity that combines three adaptive safety mechanisms: context-based safety constraints, adaptation-speed constraints, and budget-to-state safety enforcement. Context-based constraints adjust safety requirements using inferred and predicted environmental context. Adaptation-speed constraints tighten safety requirements when the rate of environmental change exceeds the agent's ability to adapt safely. Budget-to-state enforcement converts cumulative safety requirements into local state-level control constraints that can be enforced at decision time. Together, these mechanisms provide a unified approach for proactive and reactive safety adaptation in continual reinforcement learning. We evaluate the framework in simulated driving environments under stationary, seen nonstationary, and unseen nonstationary conditions. The results show that adaptive safety constraints substantially reduce safety violations under distribution shift while maintaining competitive task performance compared with unconstrained and fixed-constraint baselines. These findings suggest that safe continual reinforcement learning requires adaptive constraint mechanisms that respond not only to current state information but also to predicted environmental context, adaptation demand, and remaining safety budget.

Timofey Tomashevskiy

McMaster Centre for Software Certification Department of Computing and Software McMaster University, Canada

Non-Stationary RL Reinforcement Learning Constrained RL Safe RL Continual RL

May 13, 2026stat.ML

AIS: Adaptive Importance Sampling for Quantized RL

Reinforcement learning (RL) for large language models (LLMs) is dominated by the cost of rollout generation, which has motivated the use of low-precision rollouts (e.g., FP8) paired with a BF16 trainer to improve throughput and reduce memory pressure. This introduces a rollout-training mismatch that biases the policy gradient and can cause training to collapse outright on reasoning benchmarks. We show that the mismatch is non-stationary and acts as a double-edged sword: early in training it provides a stochastic exploration bonus, exposing the gradient to trajectories the trainer would otherwise under-sample, but the same perturbation transitions into a destabilizing source of bias as the policy concentrates. To solve this, we propose Adaptive Importance Sampling (AIS), a correction framework that adjusts the strength of its intervention on a per-batch basis. AIS combines three real-time diagnostics, namely weight reliability, divergence severity, and variance amplification, into a single mixing coefficient that interpolates between the uncorrected and fully importance-weighted gradients, suppressing the destabilizing component of the mismatch while preserving its exploratory benefit. We integrate AIS into GRPO and evaluate it on the diffusion-based LLaDA-8B-Instruct and the autoregressive Qwen3-8B and Qwen3.5-9B across mathematical reasoning and planning benchmarks. AIS matches the BF16 baseline on most tasks while retaining the 1.5 to 2.76x rollout speedup of FP8.

Jiajun Zhou, Wei Shao, Lingchao Zheng +2

Huawei · The University of Hong Kong

RL for Language Models Reinforcement Learning RL for Language Model Reasoning

May 12, 2026cs.LG

Quantifying Potential Observation Missingness in Inverse Reinforcement Learning

Inverse reinforcement learning (IRL), which infers reward functions from demonstrations, is a valuable tool for modeling and understanding decision-making behavior. Many variants of IRL have been developed to capture complexities of human decision-making, such as subjective beliefs, imperfect planning, and dynamic goals. However, an often-overlooked issue in real-world behavioral datasets is that the recorded data may be missing observations that were available to the original decision-maker. In use-inspired settings such as healthcare, this can make expert actions appear suboptimal, even when they were near-optimal given the information available at the time. As a result, the rewards learned by standard IRL may be misleading. In this paper, we identify the minimal perturbations to the recorded observations needed for the expert's actions to appear optimal. We develop a practical algorithm for this problem and demonstrate its utility for quantifying the possible extent of missing observations in behavioral datasets through extensive experiments on synthetic navigation tasks, a cancer treatment simulator, and ICU treatment data.

Leo Benac, Abhishek Sharma, Alihan Huyuk +1

School of Engineering and Applied Sciences Harvard University

Reinforcement Learning Healthcare

May 12, 2026cs.LG

ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization

The alignment of Large Language Models (LLMs) utilizes Reinforcement Learning from AI Feedback (RLAIF) for non-verifiable domains such as long-form question answering and open-ended instruction following. These domains often rely on LLM based auto-raters to provide granular, multi-tier discrete rewards (e.g., 1-10 rubrics) that are inherently stochastic due to prompt sensitivity and sampling randomness. We empirically verify the stochasticity of auto-raters that can propagate and corrupt standard advantage estimators like GRPO and MaxRL, as a noisy reward samples can skew normalization statistics and degrade the global learning signal. Empirically, sampling more rewards and taking majority voting may reduce the noise and improve performance, but this approach is computationally expensive. To address this bottleneck, we introduce

\textbf{O}

rdinal

\textbf{D}

ecomposition for

\textbf{R}

obust

\textbf{P}

olicy

\textbf{O}

ptimization (

\textbf{ODRPO}

), a framework that structurally isolates evaluation noise by decomposing discrete rewards into a sequence of ordinal binary indicators. By independently computing and accumulating advantages across these progressively challenging success thresholds, ODRPO prevents outlier evaluations from corrupting the global update while establishing an implicit, variance-aware learning curriculum. Empirically, ODRPO achieves robust performance on Qwen2.5-7B and Qwen3-4B models, outperforming baselines with relative improvements of upto 14.8% on FACTS-grounding-v2 and 7.5% on Alpaca-Evals. Critically, these gains are achieved with negligible training-time overhead, as ODRPO requires no additional compute per step compared to standard estimators. Supported by theoretical analysis confirming its optimization stability, ODRPO provides a scalable and robust framework for aligning models within the noisy, discrete evaluation landscape of modern RLAIF.

Nirmal Patel, Fei Wang, Inderjit S. Dhillon

University of Texas at Austin · Google

RL for Language Models Reinforcement Learning Robust RL Policy Learning Reward Design for RL

May 12, 2026cs.AI

Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives. However, conditioning rewards on instructions introduces a fundamental failure mode as Bellman updates couple value estimates across instruction contexts, leading to inconsistent values when instructions interrupt macro-actions. We propose Macro-Action Value Correction for Instruction Compliance (MAVIC), which corrects Bellman backups at instruction boundaries by correcting the incoming instruction objective and restoring the continuation value under the current objective. Unlike reward shaping, MAVIC modifies the bootstrapping target itself, enabling consistent value estimation under stochastic instruction switching within a unified policy. We provide theoretical analysis and an actor-critic implementation, and show that MAVIC achieves high instruction compliance while preserving base task performance in increasingly complex cooperative multi-agent environments.

Wo Wei Lin, Ethan Rathbun, Enrico Marchesini +1

Department of Computer Sciences Northeastern University United States · Department of Computer Sciences Massachusetts Institute of Technology United States

Reinforcement Learning Robust RL Cooperative MARL

May 12, 2026cs.LG

Plan Before You Trade: Inference-Time Optimization for RL Trading Agents

Reinforcement learning agents for portfolio management are typically trained and deployed as static policies, with no mechanism for using price forecasts at inference time. We propose

\text{FPILOT}

(Financial Plugin Inference-time Learning for Optimal Trading), a plugin inference-time optimization framework inspired by Model Predictive Control (MPC). Our key structural insight is that future prices mostly do not depend on one agent's portfolio allocation, so a suitable predictive model can produce a multi-step price trajectory without iterative action-conditioned rollouts as in typical reinforcement learning. At each decision step, we use the forecaster's predicted price trajectory to construct an allocation-based imagined return objective, and optimize the policy at inference-time before executing one step of the trade. Our framework is compatible with any pre-trained agent and adapts the policy to the forecaster's predictions without any retraining. Evaluated across five policy learning algorithms on the TradeMaster DJ30 benchmark,

\text{FPILOT}

produces consistent improvements in total return and return-based risk-adjusted metrics (Sharpe, Sortino, Calmar), with stochastic policies benefiting more than deterministic ones. Further, using synthetic forecasts at calibrated quality levels, we show that gains consistently improve with forecaster quality, suggesting that our performance will improve based on advances in financial forecasting.

Eun Go, Rohan Deb, Arindam Banerjee

Siebel School of Computing and Data Science University of Illinois Urbana-Champaign

Reinforcement Learning Inference-Time Optimization Predict-Then-Optimize Portfolio Optimization Finance Algorithmic Trading

May 12, 2026cs.LG

Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training

In settings where labeled verifiable training data is the binding constraint, each checked example should be allocated to the model and reward density where it is most informative. We identify a reward-density principle that governs this allocation: sparse sequence-level reward is most useful on models that can explore and discover better behavior, while dense token-level teacher supervision is better suited for compressing that behavior into a smaller deployment model. The principle yields a simple allocation rule: use scarce labeled data upstream on the strongest available teacher, then transfer the reward-shaped behavior downstream as dense supervision. We evaluate this rule through a four-stage workflow -- teacher RL, forward-KL warmup, on-policy distillation, optional post-bridge student RL -- on verifiable math with Qwen3 and Llama models. At fixed Qwen3-1.7B deployment-student size, an RL-improved 8B teacher distilled through the dense bridge outperforms direct GRPO on the same student (

79.3\%

vs.\

75.9\%

on MATH;

25.2\%

vs.\

19.8\%

on AIME~2024, avg@16), while transfer from the same teacher \emph{before} RL underperforms. A component ablation confirms that each stage is load-bearing: replacing the RL-improved teacher with a raw teacher costs

7.8

MATH points, removing the forward-KL warmup costs

1.7

, and removing on-policy distillation costs

3.3

. The teacher-quality ordering -- raw-teacher transfer

<

direct GRPO

<

RL-teacher transfer -- replicates on Llama-3.1-8B-Instruct with a Llama-3.3-70B-Instruct teacher. The operational lesson is to avoid spending scarce labeled data on the least prepared policy: use sparse reward for teacher-side discovery, dense transfer for student compression, and student-side sparse reward only after the bridge.

Yuanda Xu, Hejian Sang, Zhengze Zhou +3

Reinforcement Learning RL for Language Model Reasoning Language Model Distillation On-Policy Distillation Sparse-Reward RL Teacher-Student Learning

May 12, 2026cs.AI

Reward Hacking in Rubric-Based Reinforcement Learning

Reinforcement learning with verifiable rewards has enabled strong post-training gains in domains such as math and coding, though many open-ended settings rely on rubric-based rewards. We study reward hacking in rubric-based RL, where a policy is optimized against a training verifier but evaluated against a cross-family panel of three frontier judges, reducing dependence on any single evaluator. Our framework separates two sources of divergence: verifier failure, where the training verifier credits rubric criteria that reference verifiers reject, and rubric-design limitations, where even strong rubric-based verifiers favor responses that rubric-free judges rate worse overall. Across medical and science domains, weak verifiers produce large proxy-reward gains that do not transfer to the reference verifiers; exploitation grows over training and concentrates in recurring failures such as partial satisfaction of compound criteria, treating implicit content as explicit, and imprecise topical matching. Stronger verifiers substantially reduce, but do not eliminate, verifier exploitation. We also introduce a self-internalization gap, a verifier-free diagnostic based on policy log-probabilities, which tracks reference-verifier quality, detecting when the policy trained using the weak verifier stops improving. Finally, in our setting, stronger verification does not prevent reward hacking when the rubric leaves important failure modes unspecified: rubric-based verifiers prefer the RL checkpoint, while rubric-free judges prefer the base model. These disagreements coincide with gains concentrated in completeness and presence-based criteria, alongside declines in factual correctness, conciseness, relevance, and overall quality. Together, these results suggest that stronger verification reduces reward hacking, but does not by itself ensure that rubric gains correspond to broader quality gains.

Anas Mahmoud, MohammadHossein Rezaei, Zihao Wang +3

Scale AI

Reward Hacking Reinforcement Learning Rubric-Based RL Reinforcement Learning with Verifiable Rewards Rubric-Based Evaluation Reward Design for RL

May 12, 2026cs.AI

Towards Affordable Energy: A Gymnasium Environment for Electric Utility Demand-Response Programs

Extreme weather and volatile wholesale electricity markets expose residential consumers to catastrophic financial risks, yet demand response at the distribution level remains an underutilized tool for grid flexibility and energy affordability. While a demand-response program can shield consumers by issuing financial credits during high-price periods, optimizing this sequential decision-making process presents a unique challenge for reinforcement learning despite the plentiful offline historical smart meter and wholesale pricing data available publicly. Offline historical data fails to capture the dynamic, interactive feedback loop between an electric utility's pricing signals and customer acceptance and adaptation to a demand-response program. To address this, we introduce DR-Gym, an open-source, online Gymnasium-compatible environment designed to train and evaluate demand-response from the electric utility's perspective. Unlike existing device-level energy simulators, our environment focuses on the market-level electric utility setting and provides a rich observational space relevant to the electric utility. The simulator additionally features a regime-switching wholesale price model calibrated to real-world extreme events, alongside physics-based building demand profiles. For our learning signal, we use a configurable, multi-objective reward function for specifying diverse learning objectives. We demonstrate through baseline strategies and data snapshots the capability of our simulator to create realistic and learnable environments.

Jose E. Aguilar Escamilla, Lingdong Zhou, Xiangqi Zhu +1

Department of Electrical Engineering and Computer Science, Oregon State University, USA

RL Benchmarks Reinforcement Learning Demand Response Power Systems

May 12, 2026cs.LG

Discrete Flow Matching for Offline-to-Online Reinforcement Learning

Many reinforcement learning (RL) tasks have discrete action spaces, but most generative policy methods based on diffusion and flow matching are designed for continuous control. Meanwhile, generative policies usually rely heavily on offline datasets and offline-to-online RL is itself challenging, as the policy must improve from new interaction without losing useful behavior learned from static data. To address those challenges, we introduce DRIFT, an online fine-tuning method that updates an offline pretrained continuous-time Markov chain (CTMC) policy with an advantage-weighted discrete flow matching loss. To preserve useful pretrained knowledge, we add a path-space penalty that regularizes the full CTMC trajectory distribution, rather than only the final action distribution. For large discrete action spaces, we introduce a candidate-set approximation that updates the actor over a small subset of actions sampled from reference-policy rollouts and uniform exploration. Our theoretical analysis shows that the candidate-set error is controlled by missing target probability mass, and the induced CTMC generator error decreases as the candidate set covers more high-probability actions. Experiments on prevailing discrete action RL task show that our method provides stable offline-to-online improvement across all tasks, achieving the highest average score on Jericho with a simple GRU encoder while outperforming methods that use pretrained language models. Controlled experiments further confirm that the path-space penalty remains bounded during fine-tuning and that the CTMC generator adapts to shifted rewards faster than deterministic baselines. The candidate-set mechanism is supported by a stability analysis showing that the generator error decreases exponentially with candidate coverage.

Fairoz Nower Khan, Nabuat Zaman Nahim, Peizhong Ju

Department of Computer Science, University of Kentucky

Flow Matching Reinforcement Learning RL Fine-Tuning Offline-To-Online RL Discrete Flow Matching

May 12, 2026cs.LG

Transferable Delay-Aware Reinforcement Learning via Implicit Causal Graph Modeling

Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true propagation process of action effects. In cross-task scenarios, changes in task objectives and reward formulations further reduce the reusability of previously acquired task knowledge. To address this problem, this paper proposes a transferable delay-aware reinforcement learning method based on implicit causal graph modeling. The proposed method uses a field-node encoder to represent high-dimensional observations as latent states with node-level semantics, and employs a message-passing mechanism to characterize dynamic causal dependencies among nodes, thereby learning transferable structured representations and environment dynamics knowledge. On this basis, imagination-driven behavior learning and planning are incorporated to optimize policies in the latent space, enabling cross-task knowledge transfer and rapid adaptation. Experimental results show that the proposed method outperforms baseline methods on DMC continuous control tasks with random delays. Cross-task transfer experiments further demonstrate that the learned structured representations and dynamics knowledge can be effectively transferred to new tasks and significantly accelerate policy adaptation.

Chenran Zhao, Dianxi Shi, Yaowen Zhang +2

College of Computer Science and Technology, National University of Defense Technology, Changsha, China · Institute of Military Transportation, Tianjin, China · Intelligent Game and Decision Lab (IGDL), Beijing, China

Causal Representation Learning Reinforcement Learning Model-Based RL

May 12, 2026cs.LG

Delay-Empowered Causal Hierarchical Reinforcement Learning

Many real-world tasks involve delayed effects, where the outcomes of actions emerge after varying time lags. Existing delay-aware reinforcement learning methods often rely on state augmentation, prior knowledge of delay distributions, or access to non-delayed data, limiting their generalization. Hierarchical reinforcement learning, by contrast, inherently offers advantages in handling delays due to its hierarchical structure, yet existing methods are restricted to fixed delays. To address these limitations, we propose Delay-Empowered Causal Hierarchical Reinforcement Learning (DECHRL). DECHRL explicitly models both the causal structure of state transitions and their associated stochastic delay distributions. These are then incorporated into a delay-aware empowerment objective that drives proactive exploration toward highly controllable states, thereby improving performance under temporal uncertainty. We evaluate DECHRL in modified 2D-Minecraft and MiniGrid environments featuring stochastic delays. Experimental results show that DECHRL effectively models temporal delays and significantly outperforms baselines in decision-making under temporal uncertainty.

Chenran Zhao, Dianxi Shi, Haotian Wang +4

College of Computer Science and Technology, National University of Defense Technology, Changsha, China · Intelligent Game and Decision Lab (IGDL), Beijing, China · School of Artificial Intelligence, Hebei University of Technology, Tianjin, China +1

Reinforcement Learning Hierarchical RL RL Exploration Causal RL

May 12, 2026cs.LG

Intrinsic Vicarious Conditioning for Deep Reinforcement Learning

Advancements in reinforcement learning have produced a variety of complex and useful intrinsic driving forces; crucially, these drivers operate under a direct conditioning paradigm. This form of conditioning limits our agents' capacity by restricting how they learn from the environment as well as from others. Off-policy or learn-by-example methods can learn from demonstrators' representations, but they require access to the demonstrating agent's policies or their reward functions. Our work overcomes this direct sampling limitation by introducing vicarious conditioning as an intrinsic reward mechanism. We draw from psychological and biological literature to provide a foundation for vicarious conditioning and use memory-based methods to implement its four steps: attention, retention, reproduction, and reinforcement. Crucially, our vicarious conditioning paradigms support low-shot learning and do not require the demonstrator agent's policy nor its reward functions. We evaluate our approach in the MiniWorld Sidewalk environment, one of the few public environments that features a non-descriptive terminal condition (no reward provided upon agent death), and extend it to Box2D's CarRacing environment. Our results across both environments demonstrate that vicarious conditioning enables longer episode lengths by discouraging the agent from non-descriptive terminal conditions and guiding the agent toward desirable states. Overall, this work emulates a cognitively-plausible learning paradigm better suited to problems such as single-life learning or continual learning.

Rodney A Sanchez, Ferat Sahin, Alex Ororbia +1

Department of Electrical and Microelectronic Engineering, Rochester Institute of Technology · Department of Computer Science, Rochester Institute of Technology

Reinforcement Learning Intrinsic Motivation Learning from Demonstration

May 12, 2026cs.LG

On the Importance of Multistability for Horizon Generalization in Reinforcement Learning

In reinforcement learning (RL), agents acting in partially observable Markov decision processes (POMDPs) must rely on memory, typically encoded in a recurrent neural network (RNN), to integrate information from past observations. Long-horizon POMDPs, in which the relevant observation and the optimal action are separated by many time steps (called the horizon), are particularly challenging: training suffers from poor generalization, severe sample inefficiency, and prohibitive exploration costs. Ideally, an agent trained on short horizons would retain optimal behavior at arbitrarily longer ones, but no formal framework currently characterizes when this is achievable. To fill this gap, we formalized temporal horizon generalization, the property that a policy remains optimal for all horizons, derived a necessary and sufficient condition for it, and experimentally evaluated the ability of nonlinear and parallelizable RNN variants to achieve it. This paper presents the resulting theoretical framework, the empirical evaluation, and the dynamical interpretation linking RNN behavior to temporal horizon generalization. Our analyses reveal that multistability is necessary for temporal horizon generalization and, in simple tasks, sufficient; more complex tasks further require transient dynamics. In contrast, modern parallelizable architectures, namely state space models and gated linear RNNs, are monostable by construction and consequently fail to generalize across temporal horizons. We conclude that multistability and transient dynamics are two essential and complementary dynamical regimes for horizon generalization, and that no current parallelizable RNN exhibits both. Designing parallelizable architectures that combine these regimes thus emerges as a key direction for scalable long-horizon RL.

Asad Bakija, Florent De Geeter, Julien Brandoit +2

Dept. of Electrical Engineering and Computer Science · University of Liège · Liège, Belgium

Dynamical Systems Reinforcement Learning Partially Observable RL Recurrent Neural Networks Generalization in RL

May 12, 2026cs.LG

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it also introduces a critical failure mode for PPO-style off-policy correction. In heterogeneous training systems, the total importance ratio should ideally be decomposed into two semantically distinct factors: a \emph{training--inference discrepancy term} that aligns inference-side and training-side distributions at the same behavior-policy version, and a \emph{policy-staleness term} that constrains the update from the historical policy to the current policy. We show that practical asynchronous pipelines with delayed updates and partial rollouts often lose the required historical training-side logits, or old logits. This missing-old-logit problem entangles discrepancy repair with staleness correction, breaks the intended semantics of decoupled correction, and makes clipping and masking thresholds interact undesirably. To address this issue, we study both exact and approximate correction routes. We propose three exact old-logit acquisition strategies: snapshot-based version tracking, a dedicated old-logit model, and synchronization via partial rollout interruption, and compare their system trade-offs. From the perspective of approximate correction, we focus on preserving the benefits of decoupled correction through a more appropriate approximate policy when exact old logits cannot be recovered at low cost, without incurring extra system overhead. Following this analysis, we adopt a revised PPO-EWMA method, which achieves significant gains in both training speed and optimization performance.

Zhong Guan, Yongjian Guo, Haoran Sun +5

Tianjin University · Tsinghua University · JDT AI Infra +1

Asynchronous RL Reinforcement Learning Proximal Policy Optimization Off-Policy RL RL for LLM Agents

May 12, 2026cs.CL

Learning Agentic Policy from Action Guidance

Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy, as training signals emerge only within its in-capability region. For tasks where the base policy cannot reach reward states, additional training or external guidance is needed to recover effective learning signals. Rather than relying on costly iterative supervised fine tuning (SFT), we exploit the abundant action data generated in everyday human interactions. We propose \textsc{ActGuide-RL}, which injects action data as plan-style reference guidance, enabling the agentic policy to overcome reachability barriers to reward states. Guided and unguided rollouts are then jointly optimized via mixed-policy training, internalizing the exploration gains back into the unguided policy. Motivated by a theoretical and empirical analysis of the benefit-risk trade-off, we adopt a minimal intervention principle that invokes guidance only as an adaptive fallback, matching task difficulty while minimizing off-policy risk. On search-agent benchmarks, \textsc{ActGuide-RL} substantially improves over zero RL (+10.7 pp on GAIA and +19 pp on XBench with Qwen3-4B), and performs on par with the SFT+RL pipeline without any cold start. This suggests a new paradigm for agentic RL that reduces the reliance on heavy SFT data by using scalable action guidance instead.

Yuxiang Ji, Zengbin Wang, Yong Wang +6

1Xiamen University · 2AMAP, Alibaba Group · Work done during internship at AMAP, Alibaba Group +1

Agentic RL Reinforcement Learning LLM-Guided RL LLM Agent Training Policy Learning

May 12, 2026cs.LG

Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models

Recently, reinforcement learning (RL) has been widely applied during post-training for diffusion large language models (dLLMs) to enhance reasoning with block-wise semi-autoregressive generation. Block size has therefore become a vital factor in dLLMs, since it determines the parallel decoding granularity and affects the rollout trajectories during RL optimisation, e.g., GRPO. Instead of investigating the effect of block size during inference on individual domains, this paper studies block size from a domain conflict perspective for dLLM RL post-training in multi-domain scenarios. The main contributions are: (1) a formulation of domain block size conflict in multi-domain RL for dLLMs, which will largely affect the post-training effectiveness for rollout-based RL methods; (2) a novel dataset, Block-R1-41K is constructed with a best-improved training block size for each sample, which also induces a Block Size Conflict Score to quantitatively measure the domain conflict; (3) a new benchmark, Block-R1, for flexible RL post-training for dLLMs in both single and cross domain; and (4) a simple yet powerful cross-domain post-training method with sample-level best-improved training block sizes. Extensive experiments on 13 distinct datasets, 7 latest RL algorithms and diverse dLLM backbones are comprehensively covered in Block-R1. The benchmark is open-sourced at https://github.com/YanJiangJerry/Block-R1 with the dataset released at https://huggingface.co/datasets/YanJiangJerry/Block-R1-41K.

Yan Jiang, Ruihong Qiu, Zi Huang

The University of Queensland

RL Benchmarks Reinforcement Learning RL for Diffusion Models Diffusion Language Models

May 12, 2026cs.LG

From Generic Correlation to Input-Specific Credit in On-Policy Self Distillation

On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback to serve as its own teacher, providing dense token-level rewards without external teacher models or step-level annotations. Despite its empirical success, what this reward actually measures and what kind of credit it assigns remain unclear. Under a posterior-compatibility interpretation of feedback conditioning, standard in the implicit-reward literature, we show that the self-distillation token reward is a Bayesian filtering increment whose trajectory sum is exactly the pointwise mutual information between the response and the feedback given the input. This pMI can be raised by input-specific reasoning or by input-generic shortcuts, so we further decompose the teacher log-probability along the input axis. Based on this analysis, we propose CREDIT (Contrastive REward from DIsTillation), which isolates the input-specific component with a batch-contrastive baseline. At the sequence level, CREDIT is a teacher-side surrogate for a contrastive pMI objective that also penalizes responses remaining likely under unrelated inputs. Across coding, scientific reasoning, and tool-use benchmarks on two model families, CREDIT delivers the strongest aggregate performance at negligible additional compute.

Guobin Shen, Lei Huang, Xiang Cheng +4

Xiaohongshu Inc. · Institute of Automation, Chinese Academy of Sciences

Reinforcement Learning On-Policy Self-Distillation Token-Level Credit Assignment Language Model Post-Training Contrastive RL Mutual Information