Maximum Entropy RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 45

Oct 6, 2026cs.LG

LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL

While offline reinforcement learning (RL) enables policy optimization from static datasets without costly online interaction, it remains bottlenecked by the risk of executing out-of-distribution (OOD) actions. Recent approaches mitigate this by learning a behavior-cloning policy through flow matching and then performing RL within its constrained latent space. However, naively optimizing the latent policy can easily cause the policy to collapse into a brittle mode or exploit sharp artifacts of the learned critic. In this work, we find that entropy regularization is essential in latent-space RL for addressing these challenges. We introduce LASER, a novel offline RL algorithm that applies latent-space adjoint matching to achieve entropy-regularized latent-space RL with expressive flow policies while avoiding backpropagation through time. Through comprehensive experiments on 40 challenging OGBench tasks with varying dataset qualities, we show that LASER achieves state-of-the-art performance. Notably, LASER uses fixed method-specific hyperparameters across all tasks and outperforms the evaluated baselines, including those with task- and dataset-specific tuning, which highlights the robust applicability of LASER. Project website: https://mit-realm.github.io/laser/.

Songyuan Zhang, Oswin So, Eric Yang Yu +3

MIT · MIT Lincoln Laboratory

Reinforcement Learning Offline RL Maximum Entropy RL

Oct 1, 2026cs.LG

FERPO: Forward Entropy-Regularized Policy Optimization

Several state-of-the-art methods for online reinforcement learning in continuous control improve policies using action gradients of a learned critic. However, critics are typically trained to predict returns, and accurate value predictions do not necessarily yield accurate action derivatives, potentially leading to unreliable policy updates. We propose Forward Entropy-Regularized Policy Optimization (FERPO), an on-policy maximum entropy reinforcement learning algorithm that performs policy improvement using critic values without differentiating the critic with respect to actions. FERPO derives an optimal target action distribution from a policy-improvement objective regularized by entropy and Kullback-Leibler (KL) divergence. We then fit the actor to this target by minimizing a forward-KL objective, estimated using self-normalized importance sampling (SNIS) with actions drawn from the rollout policy. By limiting the target distribution's deviation from the rollout policy, the KL regularization helps keep these importance weights well behaved. In contrast to reverse-KL objectives, which can favor a subset of the target distribution's modes, the forward-KL objective encourages coverage of multiple high-value modes and thereby promotes exploration. Experiments and ablations on MuJoCo Playground and ManiSkill show competitive performance and sample-efficiency gains. Computational benchmarks also demonstrate faster actor updates than Relative Entropy Pathwise Policy Optimization (REPPO).

Sebastian Sanokowski, Alireza Sarmadi, Majid Khadiv

Applied and Theoretical Aspects of Robot Intelligence (ATARI) Lab, Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich

KL-Regularized RL Policy Optimization Maximum Entropy RL Continuous Control Policy Learning

Sep 28, 2026cs.LG

An analysis of Mirror-Descent Soft Actor-Critic

Soft Actor-Critic (SAC) is widely used for entropy-regularised reinforcement learning with continuous action spaces, and practical implementations perform only a few actor steps towards an evolving target. In this work, we prove convergence guarantees when the target policy arises from policy mirror descent and compare it with the classical Gibbs target. We derive sufficient conditions for the strong convexity and smoothness of the actor objective, characterised by the curvature of the

Q

-function estimate through the Legendre differential operator, and establish an

\mathcal{O}\!\left(N^{-\frac{1}{5}}\right)

best-iterate finite-time convergence rate up to actor and critic approximation errors. Moreover, the mirror-descent step size

λ

directly controls the target drift and hence actor tracking error, whereas the analogous Gibbs bound contains a non-vanishing tracking term.

Denis Zorba, Michal Valko

School of Mathematics, University of Edinburgh, United Kingdom · INRIA, Paris, France

Reinforcement Learning Online Mirror Descent Maximum Entropy RL Soft Actor-Critic

Sep 27, 2026cs.LG

Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning

Reinforcement learning with verifiable rewards (RLVR) enhances reasoning in large language models (LLMs) through outcome-level feedback, yet recent approaches to finer-grained credit assignment often require auxiliary models, additional sampling, or privileged information. Although policy entropy provides a readily available signal, prioritizing uncertain positions under both reinforcement and penalization concentrates penalties where failed responses still retain alternatives for recovery, which can suppress opportunities for exploration. To address this, we introduce Entropic Advantage Policy Optimization (EAPO), an entropy-guided credit assignment method that treats success and failure asymmetrically. Specifically, motivated by the observation that success under uncertainty is less repeatable while confident failures tend to recur, EAPO couples normalized policy entropy with the sign of the response advantage to reinforce surprising success and correct repeated failure. It assigns stronger reinforcement to high-entropy decisions in successful responses and stronger penalties to low-entropy decisions in failed responses, while attenuating penalties at uncertain positions to preserve opportunities for recovery. By redistributing the response advantage across tokens, EAPO derives token-level credit directly from existing rollout signals without additional supervision. We validate EAPO on a range of reasoning tasks across both base and reasoning backbones, demonstrating that it achieves the best overall performance. We further show that EAPO promotes more effective exploration, broadening problem coverage and generating more diverse candidate answers.

Woongyeong Yeo, Minki Kang, Chanuk Lee +3

KAIST

RL for Language Model Reasoning Credit Assignment in RL Step-Level Credit Assignment in RL Maximum Entropy RL Reinforcement Learning with Verifiable Rewards

Sep 23, 2026cs.LG

RLVR landscapes for iterated multiplications can be benign: Insights from spin-glass theory

Despite the importance of reinforcement learning with verifiable rewards (RLVR), the extent to which it can learn new reasoning capabilities remains debated. Here we study the optimization landscape of RLVR on algorithmic tasks, such as iterated group and quasigroup multiplication. To this end, we map entropy-regularized RLVR over myopic tabular policies onto an energy-based (spin-glass) model over deterministic policies. This mapping upper-bounds what RLVR can achieve, and lets us rigorously characterize the landscape in this tabular setting. We show, both theoretically and experimentally, that for a wide class of models and tasks with uncorrelated inputs, this landscape is benign, containing no local minima that could trap RLVR training. Rather, the practical difficulty of these tasks appears to stem, at least in part, from issues such as diffusive barriers and gradient-estimation error in traversing the landscape. These are genuine obstacles that can prevent a solution from being found, but they are distinct from the landscape itself being rugged. We show that these obstacles can often be mitigated through the choice of entropy regulator. Consistent with this theory, we find that a transformer trained from scratch, using only last-token rewards, successfully learns an algorithmic chain of thought for iterated non-Abelian group multiplications.

Noa Rubin, Zohar Ringel

Racah Institute of Physics The Hebrew University of Jerusalem

Reinforcement Learning Maximum Entropy RL Reinforcement Learning with Verifiable Rewards Algorithmic Reasoning

Sep 14, 2026cs.AI

SCQ: Stabilizing Conservative Q-Learning with Sigmoid-Bounded Entropy

Offline-to-online reinforcement learning reduces interaction cost for real-world robot learning but suffers from persistent value estimation instability. Existing methods address this through pessimistic regularization, lower-bound calibration, and architectural normalization, but an overlooked source of instability lies in the entropy formulation: the standard log-entropy term can become negative, destabilizing policy updates. We introduce SCQ (Sigmoid-Bounded Conservative Q-Learning), which replaces this term with a sigmoid-bounded formulation that stays strictly positive. SCQ retains conservative Q regularization and return-based lower-bound calibration, stabilizing policy optimization without sacrificing exploration. We evaluate SCQ on D4RL (Minari) benchmarks under both single-demonstration and standard dataset settings, as well as on simulation and real-world visual tasks. SCQ matches or exceeds baseline performance while exhibiting more stable training dynamics across state-based and visual benchmarks, and transfers to four real-robot platforms including manipulation, wheeled, quadruped, and humanoid systems. A direct clipping intervention that removes negative log-probability contributions, together with gradient-matched positive-score controls, indicates that positivity rather than a particular score shape alone drives much of the improvement. Project website: https://scq-rl.github.io.

Xiefeng Wu, Shu Zhang, Zhaojie Chu +1

School of Computer Science, Wuhan University, Wuhan, China · School of Electronic Information, Wuhan University, Wuhan, China · School of Internet, Anhui University, Hefei, China

Robotic RL Offline RL Maximum Entropy RL Policy Learning Offline-To-Online RL

Sep 14, 2026cs.LG

Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence

We study continuous-time and possibly high-dimensional stochastic control problems where drift coefficients and running reward functions are unknown. Due to these missing model primitives, we take the exploratory, reinforcement learning (RL) framework of Wang, Zariphopoulou, and Zhou(2020) with relaxed controls and entropy regularization. The objective is to develop theoretically grounded, efficient and scalable RL algorithms to learn both the optimal value functions (which also solve the exploratory HJB equation) and optimal exploratory feedback control policies. When the diffusion coefficients do not contain control, we employ probabilistic representations of both the optimal value function and its gradient based on an auxiliary state process depending only on the diffusion part of the original dynamics. With a delicate analysis on some properly defined mappings and their fixed points, this leads to the introduction of our policy iteration algorithms and their convergence. We demonstrate the performance of our algorithms through various numerical examples. Finally, we study a special control-dependent diffusion case where probability representation of the Hessian is called for.

Jin Ma, Gaozhan Wang, Jianfeng Zhang +1

Department of Mathematics, University of Southern California, Los Angeles, CA 90089 · Department of Industrial Engineering and Operations Research, Columbia University, New York, NY 10027

Reinforcement Learning Stochastic Optimal Control Policy Iteration RL Exploration Maximum Entropy RL Continuous-Time RL

Aug 7, 2026math.OC

Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control

Wasserstein policy gradient (WPG) updates state-conditional action laws by transport in the action space. We study entropy-regularized discounted linear-quadratic (LQ) control. A Bellman verification argument shows that the unrestricted problem has a linear-Gaussian optimal policy, and the discounted-occupancy-weighted statewise Wasserstein gradient is tangent to this policy class. WPG therefore reduces exactly to a finite-dimensional ODE for the feedback gain and action covariance. We prove that this ODE is globally well posed and converges exponentially from every admissible initialization. For each fixed LQ problem, the exponent has a positive limit as the entropy temperature tends to zero and contains no perturbative factor of the form

\exp(-c/τ)

, while retaining the usual dependence on the conditioning of the control problem.

Zhaoyu Zhu, Rui Gao, Shuang Li

University of Illinois Urbana-Champaign · The University of Texas at Austin · The Chinese University of Hong Kong, Shenzhen

Maximum Entropy RL Policy Gradient Methods Linear Quadratic Regulator

Jul 20, 2026cs.LG

Distributional Soft Bellman Operator under the Cramér Geometry

Distributional soft policy iteration (DSPI) provides an important framework for combining distributional reinforcement learning (DRL) with maximum-entropy control, in which the policy evaluation step is governed by a distributional soft Bellman operator acting on entropy-regularised returns. Theoretical analysis of such an evaluation step requires a probability metric under which Bellman updates can be controlled, typically by showing that the operator contracts the distance between any two candidate return-distribution estimates. In this paper, we focus on the Cramér geometry, a cumulative distribution function (CDF)-based metric with an

L^2

structure, and study whether the fixed-policy distributional soft Bellman operator has this contraction property and hence a unique fixed point under this metric. Working directly on an admissible CDF field domain, we formulate the CDF-level distributional soft Bellman operator, prove that it is a

\sqrtγ

-contraction, and obtain the corresponding unique fixed point together with convergent iterative policy evaluation. The CDF formulation also shows that this finite-Cramér-domain property follows from a uniform first-moment condition on the combined one-step reward entropy shift, rather than from separate uniform boundedness assumptions on the reward and entropy terms. We then transport the same evaluation problem to the spectral domain by conjugation, obtaining an equivalent Hilbert-space representation of the same decision process. Taken together, these results identify the Cramér-geometric Bellman fixed point associated with the policy-evaluation step of DSPI, providing a reference point for studying approximate critics, evaluation error, and critic-loss design in DSPI-style algorithms.

Keru Wang, Yixin Deng, Yao Lyu +2

School of Electrical and Electronic Engineering, University College Dublin, Dublin, Ireland · School of Vehicle and Mobility, Tsinghua University, Beijing, China · College of Artificial Intelligence, Tsinghua University, Beijing, China

Distributional RL Maximum Entropy RL

Jul 19, 2026cs.LG

Rationalizing Boltzmann Rationality: An Axiomatic Characterization of Entropy-Regularized Policies

The softmax policy

π(a \mid s) \propto \exp(βQ(s,a))

is the default model of stochastic choice in reinforcement learning (RL). Various justifications based on robustness, exploration, and optimization have been offered in the RL literature, but none uniquely derives the softmax form from first principles. This leaves a basic tension unresolved: the entropy bonus in the soft Bellman equation violates the Independence axiom that underwrites the Markov decision process (MDP) reward structure. We dissolve this tension by distinguishing two kinds of randomness: chance and choice. By restricting von Neumann-Morgenstern (VNM) Independence to environmental lotteries over base prospects, we show that imposing independence of irrelevant alternatives (IIA) and monotonicity on the policy and value functions at choice nodes uniquely determines the Boltzmann policy, the entropy-regularized representation, and the soft Bellman equation. The choice between the soft and hard Bellman equations thus reduces to a design decision: whether the agent values its own ability to choose. We develop RL-specific consequences, including return monotonicity and convergence under generalized discounting, and synthesize the independent lines from economics and information theory that arrive at the same structure, offering a normative assessment of when IIA is appropriate for agent design.

Silviu Pitis

University of Michigan

Markov Decision Processes Maximum Entropy RL Decision-Making under Uncertainty

Jul 18, 2026cs.CL

Group Entropy-Controlled Policy Optimization

Entropy control has become an effective tool in reinforcement learning (RL) of large language models (LLMs), helping balance exploration-exploitation trade-off during alignment process. Such RL paradigm is often conducted on mixtures of heterogeneous tasks, which induce distinct entropy regimes under the same policy, making global or token-level entropy regulation insufficient to corresponding heterogeneous needs of exploration. This heterogeneity further makes GRPO-style normalized advantages induce an entropy-dependent bias, making advantage signals across prompt groups statistically non-comparable. To address this issue, we propose Group Entropy-Controlled Policy Optimization (GEPO), a lightweight extension to GRPO that uses group entropy, estimated from existing grouped samples to perform entropy-conditioned asymmetric advantage shaping. GEPO attenuates positive advantages in low-entropy groups to reduce over-exploitation, and negative advantages in high-entropy groups to preserve exploration, with adaptive thresholds derived from historical entropy statistics. Extensive experiments on two base models across thirteen benchmarks spanning mathematics, physics, science, code generation, and instruction following show that GEPO consistently outperforms GRPO and recent entropy-controlled methods, delivering balanced cross-task improvements while preserving task-specific exploration levels throughout training.

Guangran Cheng, Chengqi Lyu, Songyang Gao +2

Shanghai AI Laboratory

RL for Language Models Group Relative Policy Optimization Maximum Entropy RL Multi-Task RL

Jul 8, 2026cs.LG

Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning

Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, existing efforts largely focus on single-task settings, whereas real-world deployment necessitates a generalist agent capable of solving multiple tasks simultaneously. In this work, we identify a critical yet underexplored phenomenon in multi-task agentic RL: different tasks can exhibit exploration-exploitation pace mismatch. Specifically, easier tasks may converge early to low-entropy policies that hinder learning on harder tasks, while harder tasks can, in turn, push easier tasks back toward high-entropy exploration. This back-and-forth interaction creates inter-task entropy crossovers and frequent entropy spikes. Inspired by this observation, we introduce Entropy Pacing Policy Optimization (EPPO) for multi-task agentic LLMs, which coordinates entropy across tasks to stabilize multi-task optimization. At the core of EPPO is a task-wise dynamic clipping mechanism that replaces the fixed clipping threshold in Group Relative Policy Optimization (GRPO) with a task entropy-aware adaptive bound, tightening updates for over-confident tasks while relaxing them for under-explored ones. Experiments on the multi-task agentic benchmarks demonstrate that the proposed EPPO yields results superior to its counterparts.

Zetian Hu, Shunyu Liu, Junjie Zhang +4

Generative AI Lab, College of Computing and Data Science, Nanyang Technological University, Singapore 639798 · Tongyi Lab, Alibaba Group

Agentic RL Group Relative Policy Optimization Maximum Entropy RL Multi-Task RL RL for LLM Agents

Jul 3, 2026math.OC

Entropy Regularization Improves Policy Robustness in Continuous-Time Reinforcement Learning

Entropy regularization is widely used in continuous-time reinforcement learning (RL) to reduce sensitivity to environmental perturbations, yet its robustness benefits lack a rigorous theoretical foundation. This paper establishes the first robustness guarantees for entropy-regularized continuous-time Markov decision processes. We show that maximizing an entropy-regularized objective yields a lower bound on a worst-case robust RL problem with joint reward and transition perturbations. We analytically characterize the induced robust sets and prove that they expand monotonically with the regularization strength, justifying the empirical observation that stronger entropy improves robustness. In contrast to prior discrete-time analyses, our results remove the intractable state-distribution entropy term and provide guarantees invariant to action frequency. Experiments on queueing network control and market making confirm our theory, showing that entropy-regularized policies outperform greedy and

ε

-greedy baselines under dynamics perturbations.

Jialun Cao, Fernando Acero, David Šiška +1

School of Mathematics, University of Edinburgh, United Kingdom. · J.P. Morgan AI Research, United Kingdom. · Department of Mathematics, Imperial College London, United Kingdom.

Robust Markov Decision Processes Maximum Entropy RL Continuous-Time RL Distributionally Robust RL Robust RL

Jul 3, 2026cs.LG

ACPO: Adaptive Credit Policy Optimization via Fine-Grained Surrogate Entropy

Reinforcement Learning (RL) has substantially improved the reasoning ability of large language models (LLMs), but sparse outcome rewards still make token-level credit assignment difficult. Existing scalable RL methods typically assign trajectory-level rewards uniformly across tokens, while recent entropy-aware approaches either rely on coarse detached heuristics or directly optimize true entropy, which can introduce non-local gradient components misaligned with sampled-token policy updates. We propose Adaptive Credit Policy Optimization (ACPO), a token-level credit assignment framework based on a mode-local surrogate entropy. ACPO asymmetrically modulates policy updates by emphasizing uncertain decisions in successful rollouts and overconfident tokens in failed rollouts. We show that the surrogate admits deterministic entropy bounds and, under modal alignment and proximal updates, preserves the policy-gradient direction to leading order. Experiments on mathematical reasoning and coding benchmarks, including AIME 2025 and HumanEvalPro, show that ACPO consistently improves over strong RL baselines such as DAPO, GTPO, and SAPO.

Zijun Xie, Yuyang You, Yongzhi Li +6

Peking University · Baidu Inc. · Kuaishou Inc.

Token-Level Credit Assignment RL for Language Model Reasoning Step-Level Credit Assignment in RL Maximum Entropy RL Policy Gradient Methods Sparse-Reward RL+1

Jun 27, 2026cs.LG

Entropy-Regularized Reinforcement Learning for Linear-Quadratic Stackelberg Differential Games in Regime-Switching Diffusion Models

Stackelberg differential games (SDGs) provide a powerful framework for hierarchical decision-making in stochastic and continuous-time environments, yet their solution remains computationally challenging due to the complexity of traditional dynamic programming and Hamilton-Jacobi-Bellman-Isaacs (HJBI) methods, especially in high-dimensional systems. This paper proposes an entropy-regularized reinforcement learning (ERRL) approach for linear-quadratic SDGs (LQ-SDGs) within a continuous-time diffusion framework governed by Markovian regime switching. The key innovation lies in deriving exploratory weakly-coupled HJBI equations with entropy regularization, which promotes stochastic policies that actively avoid suboptimal equilibria -- a limitation of classical SDG methods. Neural networks are integrated to approximate regime-dependent value functions and solve high-dimensional partial differential equations (PDEs) efficiently, while a novel sampling technique enhances computational tractability. Numerical results demonstrate the effectiveness of the framework compared to conventional approaches, particularly in escaping suboptimal traps through exploratory policies. The study highlights the critical role of entropy regularization and neural network approximations in achieving robust solutions for hierarchical decision-making problems under abrupt environmental shifts.

Congde Hu, Danping Li, Lin Xu +1

School of Mathematics and Statistics, Anhui Normal University, Wuhu, Anhui 241002, China · School of Statistics, Key Laboratory of Advanced Theory and Application in Statistics and Data Science-MOE, Faculty of Economics and Management, East China Normal University, Shanghai, China · School of Mathematics, Southeast University, Nanjing, Jiangsu 211189, China

Stackelberg Games Maximum Entropy RL Continuous-Time RL

Jun 27, 2026cs.LG

Entropy Regularized Reinforcement Learning for Zero-Sum Stochastic Differential Games in a Regime-Switching Jump-Diffusion Process

To address parameter misspecification and sudden structural environmental changes in conventional stochastic differential game (SDG) frameworks, this paper introduces a distributional control approach that characterizes optimal strategies as probability distributions over actions, conditioned on the continuous state, the discrete regime state, and parameters. This forms a reinforcement learning framework for entropy-regularized zero-sum stochastic differential games (ERRL-ZSSDGs) in a regime-switching jump-diffusion process. Using the dynamic programming principle (DPP), we derive the associated coupled systems of Hamilton-Jacobi-Bellman-Isaacs (HJBI) equations, from which equilibrium strategies are expressed via gradients of the value function. For linear-quadratic problems, semi-analytical solutions for both value function and equilibrium strategies are obtained by solving a system of coupled ordinary differential equations (ODEs). In more general settings, an Actor-Critic policy improvement algorithm is developed to approximate the value functions and equilibrium policies across different regimes. The method is applied to an investment game, and numerical examples illustrate the effect of the temperature parameter and regime transitions on optimal policies and values.

Congde Hu, Zhuo Jin, Danping Li +1

School of Mathematics and Statistics, Anhui Normal University, Wuhu, 241002, Anhui, China. · Department of Actuarial Studies and Business Analytics, Macquarie University, Sydney, 2109, NSW, Australia. · School of Statistics, KLATASDS-MOE, China Inclusive Ageing Finance Research Center, East China Normal University, Shanghai, 200062, Shanghai, China.

Zero-Sum Games Maximum Entropy RL

Jun 21, 2026cs.LG

Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching

Diffusion policies have recently emerged as a powerful paradigm for representing complex action distributions in reinforcement learning (RL). However, their application to online RL remains limited by the challenge of scalable training in the absence of ground-truth data, where standard optimization techniques such as score matching are not directly applicable. In this work, we introduce a highly efficient algorithm for optimizing diffusion policies by leveraging recent advances in stochastic optimal control. Our approach is based on adjoint matching, which enables simulation-free training and circumvents the need for explicit likelihood estimation or costly backpropagation through the diffusion process. Furthermore, we propose several extensions that improve the robustness and stability of the method in practical settings. Empirical results demonstrate that our approach achieves competitive performance while significantly reducing computational overhead, making diffusion policies more viable for online RL scenarios.

Serge Thilges, Onur Celik, Denis Blessing +2

Autonomous Learning Robots, Karlsruhe Institute of Technology

Diffusion Policy Maximum Entropy RL RL for Diffusion Models

Jun 17, 2026cs.LG

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

Reinforcement Learning with Verifiable Rewards algorithms like GRPO have emerged as the dominant post-training paradigm for complex reasoning in LLMs, yet commonly suffer from policy entropy collapse during training. We conduct a first-order gradient analysis of token-level entropy dynamics under GRPO and identify a token-level credit assignment mismatch: the per-token entropy variation decomposes into the product of the trajectory-level advantage and an entropy sensitivity function over the next-token distribution, yielding an advantage-surprisal four-quadrant structure and a near-criticality property. Motivated by it, we propose STARE (Surprisal-guided Token-level Advantage Reweighting for policy Entropy stability), which identifies entropy-critical token subsets via batch-internal surprisal quantiles, selectively reweights their effective advantages, and incorporates a target-entropy closed-loop gate for stable entropy regulation. Across model scales from 1.5B to 32B and three task families (Short CoT, Long CoT, and Multi-Turn Tool Use), STARE sustains stable RL training over thousands of steps while maintaining policy entropy within the target band. On AIME24 and AIME25, STARE outperforms DAPO and other competitive baselines by 4%-8% in average accuracy, with reflection tokens and response length growing in tandem, indicating sustained exploration-exploitation balance that further unlocks RL training potential.Code is available at https://github.com/hp-luo/STARE.

Haipeng Luo, Qingfeng Sun, Songli Wu +4

Shenzhen International Graduate School, Tsinghua University · Tencent Hunyuan

RL for Language Model Reasoning Maximum Entropy RL Reinforcement Learning with Verifiable Rewards Policy Gradient Methods

Jun 15, 2026cs.LG

Maximum Entropy Inverse Reinforcement Learning for Mean-Field Games with Average Reward

We study inverse reinforcement learning for discrete-time, infinite-horizon mean-field games (MFGs) under an average-reward criterion. Expert demonstrations are assumed to arise from a stationary mean-field equilibrium under an unknown reward, and the goal is to recover a policy explaining the observed behaviour via the maximum causal entropy principle. We formulate the inverse problem by enforcing consistency with the expert mean-field term and long-run feature expectations, treating two reward classes within a unified occupation-measure framework. For finite-dimensional linear rewards, we give a convex dual reformulation with an explicit log-partition objective, and prove smoothness and curvature properties justifying constant-step-size gradient descent. For infinite-dimensional RKHS rewards, we develop a Lagrangian relaxation whose inner-maximising policy is characterised by a soft Bellman equation. The main obstacle is the absence of a discount-factor contraction. We resolve this by introducing a minorisation-based sub-stochastic kernel that yields a strict contraction of the soft Bellman operator. We establish Fréchet differentiability and Lipschitz smoothness of the log-likelihood score, leading to a gradient ascent algorithm with convergence guarantees. Two numerical examples, a malware-spread MFG and an RKHS-based consumer-choice model, show that the recovered policies closely match expert behaviour.

Şevket Kaan Alkır, Naci Saldı, Berkay Anahtarcı +1

Department of Mathematics Bilkent University 06800 Ankara, Turkey · Department of Mathematical Engineering Özyeğin University 34794 Istanbul, Turkey

Reinforcement Learning Average-Reward RL Mean Field Games Maximum Entropy RL

Jun 9, 2026cs.LG

Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations

The financial market is a typical low signal-to-noise ratio (SNR) setting, which often destabilizes off-policy maximum-entropy methods like Soft Actor-Critic (SAC). Specifically, noisy state representations may produce unreliable Q-value estimates, and bootstrapping amplifies these errors, forming a failure mode we call the "Financial Entropy Trap". In this paper, we propose FPQC-SAC, an efficient and plug-and-play SAC variant that places a compact and bounded Parameterized Quantum Circuit (PQC) before the actor and critic networks to constrain feature propagation at the representation level, rather than filtering raw inputs or regularizing Q-values after bootstrapping. Notably, FPQC-SAC reduces the impact of extreme market fluctuations on Bellman target estimation, while trainable quantum entanglement preserves flexible cross-asset interactions. Empirical evaluations on real-world portfolio management tasks demonstrate that FPQC-SAC substantially enhances out-of-sample stability and cumulative returns by achieving a 66.89% relative gain in cumulative return over standard unconstrained SAC and outperforms the best continuous-control deep reinforcement learning baseline by approximately 27%. Open-source code is available at https://github.com/ZeyuLIU-UST/FPQC-SAC-main.

Zeyu Liu, Xuanzhi Feng, Sing Kwong Lai +6

The Hong Kong University of Science and Technology

Quantitative Finance Quantum Machine Learning Maximum Entropy RL Quantum RL Off-Policy RL Finance

Jun 7, 2026cs.AI

PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR

Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning but often suffers from rapid policy-entropy collapse, where the policy prematurely concentrates on narrow high-probability reasoning paths. While global entropy regularization can encourage exploration, uniformly increasing entropy across all token positions is inefficient for long reasoning trajectories, where many tokens are not decision-relevant. We propose Position-Aware Entropy Calibration (PAEC), a token-level entropy-management framework that constructs a soft mask from local top-p entropy and top-two candidate competition, and applies an anchor-based lower-bound penalty to prevent selected-position entropy collapse. Experiments on five mathematical reasoning benchmarks show that PAEC improves macro-average majority-vote performance over strong RLVR baselines, with clear gains on AIME-style tasks. Our results suggest that entropy management in reasoning RL should be formulated as selective exploration allocation over decision-sensitive positions rather than uniform randomness injection.

Shumeng Yang, Yisu Liu, Jiayi Zheng +2

Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · School of Artificial Intelligence, Beijing University of Posts and Telecommunications +2

RL for Language Model Reasoning Maximum Entropy RL Reinforcement Learning with Verifiable Rewards LLM Reasoning

Jun 3, 2026cs.LG

Selective-Advantage Entropy-Adaptive Horizon GRPO: Asymmetric Token-Level Discounting for Efficient Reinforcement Learning of Language Models

Group Relative Policy Optimisation (GRPO) has emerged as an effective reinforcement-learning algorithm for aligning language models on reasoning tasks, but it treats every token position and every sampled rollout symmetrically. We introduce two complementary extensions: (i) Adaptive-Horizon GRPO (AH-GRPO), which weights each token's policy gradient using a cumulative entropy-based discount that reduces the effective horizon when the model is uncertain, and (ii) Selective-Advantage AH-GRPO (SA-AH-GRPO), which applies this discounting only to negative-advantage rollouts, leaving positive-advantage, successful trajectories unattenuated. We evaluate standard GRPO with alpha = 0, AH-GRPO with alpha = 0.5, and SA-AH-GRPO with alpha = 0.5 on the GSM8K mathematical reasoning benchmark using both Qwen 2.5-1.5B-Instruct and Qwen 2.5-3B-Instruct fine-tuned with LoRA. On the 3B model, SA-AH-GRPO achieves Pass@1 = 0.858 at its peak at step 30 and maintains 0.846 at 180 steps, with training variance reduced to 0.0246, a 3.6 times reduction relative to GRPO while matching its peak accuracy. On the 1.5B model, SA-AH-GRPO achieves a peak Pass@1 of 0.686, improving over the zero-shot baseline of 0.637. Our analysis shows that asymmetric discounting preserves the full gradient signal on correct solutions, prevents entropy collapse, and substantially stabilises training, suggesting a principled inductive bias for reinforcement learning with verifiable rewards on structured generation tasks.

Chirag Chawla, Rohan Charudatt Salvi, Madhav S. Baidya

Indian Institute of Technology (BHU), Varanasi, India · Department of Computer Science, University of Illinois Chicago, IL 60607, USA

Reinforcement Learning RL for Language Model Reasoning Group Relative Policy Optimization Maximum Entropy RL

May 29, 2026cs.LG

FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance

Maximum entropy reinforcement learning (MaxEnt-RL) enables robust exploration, yet practical implementations often restrict policies to simple Gaussians. While recent approaches incorporate expressive generative policies via importance-weighted supervised learning, they are prone to importance weight collapse, which limits their scalability in high-dimensional action spaces. Our key insight is to mitigate this limitation by localizing the sampling region, avoiding the weight degeneracy induced by importance sampling over the entire action space. To instantiate this insight, we introduce \textbf{FLAG} (\textbf{F}low policy with \textbf{L}atent-\textbf{A}ugmented \textbf{G}uidance). FLAG augments the state space with a flow latent variable and optimizes a provably consistent proxy MaxEnt-RL objective. We empirically demonstrate that FLAG enables expressive policy optimization with limited importance samples and scales to high-dimensional control tasks. Furthermore, FLAG achieves state-of-the-art performance across challenging benchmarks. Our project webpage: https://flag-rl.github.io/

Sungha Kim, Gawon Lee, Jusuk Lee +3

Seoul National University · Georgia Institute of Technology

RL Control Maximum Entropy RL Policy Learning

May 25, 2026cs.LG

Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning

Wasserstein policy gradient (WPG) is a policy optimization method for reinforcement learning (RL) that exploits the optimal-transport geometry of action distributions. For the entropy-regularized RL objective, WPG evolves each state-conditional policy by transporting it along the action gradient of the soft Q-function together with a Langevin-type diffusion. Despite its appeal for continuous-control problems, its global convergence properties remain poorly understood. Standard Langevin analyses do not directly apply, because the RL objective depends on the policy through the Bellman recursion rather than through a static convex functional, and the Langevin drift is determined by the soft Q-function, whose regularity must be controlled along the policy iterates. In this paper, we develop a global convergence theory for WPG by exploiting the Bellman structure of entropy-regularized RL. We show that the role usually played by convexity can be replaced by a Bellman-based argument: the soft Bellman residual admits a statewise KL representation with respect to a Gibbs policy; Bellman contraction relates this residual to the global optimality gap; and a Bellman resolvent identity connects value improvement to relative Fisher information. Combined with a uniform log-Sobolev inequality (LSI) for the evolving Gibbs family, these ingredients yield a distributional Polyak--Łojasiewicz condition. We further establish the regularity and uniform bounds needed to control the discretization error, thereby obtaining geometric contraction up to a discretization bias. Conceptually, our analysis shows that although entropy-regularized RL is not convex in the usual flat sense, the Bellman recursion induces a favorable Polyak--Lojasiewicz-type (PL) geometry that supports global convergence of WPG.

Zhaoyu Zhu, Rui Gao, Shuang Li

Shanghai Jiao Tong University · The University of Texas at Austin · The Chinese University of Hong Kong, Shenzhen

Optimization Convergence Analysis Wasserstein Gradient Flows Maximum Entropy RL Policy Gradient Methods Stochastic Optimization Convergence

May 24, 2026cs.LG

Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs

We study the global convergence of policy gradient for infinite-horizon entropy-regularized Markov decision processes (MDPs) with continuous state and action spaces. We consider log-linear softmax policies with linear function approximation, which extend the tabular softmax parameterization while retaining a tractable policy class. Under

Q^π_τ

-realizability for the regularized state-action value function, we first establish a non-uniform Polyak--Łojasiewicz (PŁ) inequality. The non-uniformity arises through degeneracy of constants associated with the policy geometry, namely the Fisher information matrix or an uncentered feature covariance matrix. We then identify two feature regimes under which this non-uniform constant can be bounded along the gradient flow. For full-affine-span features, we prove radial unboundedness of the KL regularizer and show that the smallest eigenvalue of the Fisher information matrix remains bounded below by an initialization-dependent positive constant. For simplex-valued features, we prove an analogous radial unboundedness result in the subspace orthogonal to the all-ones vector and obtain a uniform lower bound for the smallest eigenvalue of the uncentered covariance matrix. These results imply global linear convergence of the regularized objective along the gradient flow, i.e. suboptimality decaying as

\mathcal{O}(e^{-Ct})

for some

C>0

. Our analysis extends the global convergence theory of entropy-regularized softmax policy gradient beyond the tabular setting of Agarwal et al. (2020); Bhandari and Russo (2024); Mei et al. (2020).

Ziyue Chen, David Šiška, Lukasz Szpruch

Policy Gradient Reinforcement Learning Maximum Entropy RL Continuous-Time RL

May 23, 2026cs.LG

Refined Analysis of Entropy-Regularized Actor-Critic

In this paper, we study the role of the critic in actor--critic for entropy-regularized, finite, discounted environments. We establish that, when the critic is exact, using the latter as a baseline is a variance-reduction method in a strong sense. In this case, actor--critic with stochastic gradients matches the sample complexity of deterministic policy gradient, reaching an

ε

-optimal regularized value with

\tilde{O}(\log(1/ε))

samples. In practice, the critic is learned alongside the actor: the variance of the actor update is then influenced by the critic's variance and bias. Specifically, when the critic has a sufficiently small error, the variance reduction and rapid convergence are preserved. This suggests to learn the critic first, keeping it up to date after each actor update, underscoring the crucial role of accurate critic estimation in actor--critic methods.

Safwan Labbi, Paul Mangold, Daniil Tiapkin +1

CMAP, CNRS, École Polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France · Université Paris-Saclay, CNRS, LMO, 91405, Orsay, France · Google DeepMind +2

Reinforcement Learning Maximum Entropy RL Policy Gradient Methods Actor-Critic Methods Sample-Efficient RL

May 21, 2026cs.LG

A note on convergence of Wasserstein policy optimization

Wasserstein Policy Optimization (WPO) is a recently proposed reinforcement learning algorithm that leverages Wasserstein gradient flows to optimize stochastic policies in continuous action spaces. Despite its empirical success, the theoretical convergence properties of WPO in environments with continuous state and action spaces have yet to be fully established. In this note, we argue that WPO within the framework of entropy-regularised Markov Decision Processes converges linearly. This is done by leveraging recent advances in mean-field analysis for convergence of gradient flows using log-Sobole inequalities. Assuming existence of sufficiently regular solution to the gradient flow equation we demonstrate monotonic energy dissipation along the flow and establish a local log-Sobolev inequality. Ultimately, these properties allow us to argue that the value function should converge linearly to the global optimum.

David Šiška, Yufei Zhang

School of Mathematics, University of Edinburgh, United Kingdom · Department of Mathematics, Imperial College London, United Kingdom

Wasserstein Gradient Flows Policy Optimization Maximum Entropy RL Stochastic Optimization Convergence

May 20, 2026cs.LG

Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent

Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative policies are more expressive, but often require iterative sampling or lack tractable entropy estimates. On the optimisation side, SAC-style soft policy improvement and mirror descent (MD) can be viewed as minimising different KL divergences: the former moves the policy towards a value-induced Boltzmann distribution, while the latter regularises each update against the previous policy. Combining entropy regularisation with an MD constraint is therefore attractive, as it supports exploration while stabilising policy improvement; however, the resulting target can be multimodal and is poorly matched by unimodal Gaussian policies. We propose Stochastic MeanFlow Policies (SMFP), a one-step generative policy class that maps Gaussian noise to actions through a MeanFlow transformation. This stochastic reparameterisation yields a tractable entropy surrogate and allows MeanFlow policies to be trained within off-policy mirror descent under a unified objective for exploratory yet stable improvement. Across seven MuJoCo benchmarks, SMFP improves over Gaussian and generative baselines while retaining single-step inference efficiency.

Zeyuan Wang, Da Li, Yulin Chen +6

Laboratory for Big Data and Decision, National University of Defense Technology, China · Samsung AI Center Cambridge, UK · Queen Mary University of London, UK +3

Reinforcement Learning Maximum Entropy RL Mean Flow RL for Generative Models Off-Policy RL

May 20, 2026cs.LG

Behavior-Consistent Deep Reinforcement Learning

Reinforcement learning (RL) often exhibits high variance across training runs, leading to unreliable performance and posing a major challenge to deployment in real-world domains. In this work, we address the challenge of cross-run policy divergence by formalizing the problem of behavior-consistent RL, where the objective is to obtain policies that are both high-performing and distributionally similar across training runs. Our key observation is that maximum-entropy RL provides a direct mechanism for controlling behavioral divergence by anchoring runs to a common (uniform) prior. We prove that, for Boltzmann policies, choosing the temperature proportional to

Q

-function disagreement bounds the pairwise KL divergence between the induced policies. However, we also show that naïvely increasing entropy might impair policy optimization while amplifying off-policy error. Building upon these observations, we propose

Q

-value Expectile Disagreement (QED), a state-dependent temperature schedule that uses double-critic disagreement as a single-run proxy for cross-run disagreement. Empirically, we demonstrate that across 18 continuous-control tasks, QED reduces across-run divergence by two orders of magnitude without sacrificing performance, resulting in a considerable reduction in return variance at modest sample-efficiency costs.

Marcel Hussing, Liv G. d'Aliberti, Claas Voelcker +2

University of Pennsylvania · Princeton University · University of Texas at Austin

Reinforcement Learning Policy Optimization Maximum Entropy RL Policy Learning Entropy Regularization

May 12, 2026cs.LG

Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control

Policy entropy has emerged as a fundamental measure for understanding and controlling exploration in reinforcement learning with verifiable rewards (RLVR) for LLMs. However, existing entropy-aware methods mainly regulate entropy through global objectives, while the token-level mechanism by which sampled policy updates reshape policy entropy remains underexplored. In this work, we develop a theoretical framework of entropy mechanics in RLVR. Our analysis yields a first-order approximation of the entropy change, giving rise to entropy polarity, a signed token-level quantity that predicts how much a sampled update expands or contracts entropy. This analysis further reveals a structural asymmetry: reinforcing frequent high-probability tokens triggers contraction tendencies, whereas expansive tendencies typically require lower-probability samples or stronger distributional correction. Empirically, we show that entropy polarity reliably predicts entropy changes, and that positive and negative polarity branches play complementary roles in preserving exploration while strengthening exploitation. Building on these insights, we propose Polarity-Aware Policy Optimization (PAPO), which preserves both polarity branches and implements entropy control through advantage reweighting. With the empirical entropy trajectory as an online phase signal, PAPO adaptively reallocates optimization pressure between entropy-expanding and entropy-contracting updates. Experiments on mathematical reasoning and agentic benchmarks show that PAPO consistently outperforms competitive baselines, while delivering superior training efficiency and substantial reward improvements.

Jiazheng Zhang, Ziche Fu, Junrui Shen +17

Fudan NLP Group, Honor Device Co., Ltd · University of Hong Kong, Shanghai Jiao Tong University and Tencent Hunyuan

RL for Language Model Reasoning Policy Optimization Maximum Entropy RL Reinforcement Learning with Verifiable Rewards