Overview

Policy optimization studies how to update a decision-making rule so it earns higher rewards while meeting constraints such as safety, fairness, or limited data. Common approaches include policy gradients, actor-critic methods, trust regions and mirror descent, as well as policy iteration and newer generative-policy methods. Work spans continuous-control benchmarks such as MuJoCo, offline and multi-agent settings, and language-model training for mathematical reasoning, coding, and tool use, where token-, segment-, or trajectory-level rewards guide updates. A central challenge is balancing effective exploration and sample reuse with stable updates, useful credit assignment, and improvements that carry over from training to deployment.

Latest papers

CardsList

237 papers18 papers in the last four weeks, down 51% on the four weeks before. 0.1% of all new papers.

  1. Improved Regret via Variance-Aware Policy Optimization in Adversarial MDPs

    Nov 12, 2026Ofir Schlisselberg, Alon Cohen, Yishay MansourRegret Minimization in RLMarkov Decision Processes

  2. A Theory of Policy Optimization in Post-Training: Coverage Collapse and Reference Resets

    Nov 10, 2026Audrey Huang, Nan Jiang, Sham M. Kakade +3Policy OptimizationRL Post-Training

  3. Audited Gradients, Anchored Policies: Model-Based Reinforcement Learning for Efficient Flow Control

    Nov 9, 2026Ruige Kong, Stefania FrescaModel-Based RLSurrogate-Assisted Optimization

  4. Ordered Policy Optimization

    Nov 6, 2026Dongkyu Derek Cho, Pan XuPolicy OptimizationProximal Policy Optimization

  5. Foresee to Trade: Forecast-Augmented Policy Optimization for Portfolio Management

    Nov 5, 2026Zeyu Liu, Xuanzhi Feng, Haoran Xu +7Policy OptimizationPortfolio Optimization

  6. Learning Multi-Agent Orchestration:Higher-Order Interactions in Policy Improvement

    Nov 5, 2026Kaixuan Liu, Guojun XiongMulti-Agent OrchestrationLLM Agent Orchestration

  7. MAPO: Mixture of Experts with Alternating Policy Optimization for Universal Humanoid Motion Tracking

    Nov 2, 2026Seonghyeon Lim, Hyeonwoo Lee, Mincheol Kim +2Humanoid Motion TrackingRobot Policy Learning

  8. Zeroth-Order Policy Optimization for Scheduling in Queueing Networks

    Oct 31, 2026Deyi Wang, Qining Zhang, Lei YingPolicy OptimizationQueueing Theory

  9. Hi-CoLA: High Confidence Lower Bound Approximation Based Reinforcement Learning for Flex-Route Transit Operation Control

    Oct 31, 2026Qi Kang, Haris N. Koutsopoulos, Hongliang Guo +1RL ControlSafe RL

  10. Conservative Policy Iteration For Zero-Sum POSGs

    Oct 27, 2026Erwan C. Escudie, Matthia Sabatelli, Jilles Steeve DibangoyePartially Observable Stochastic GamesZero-Sum Games

  11. PolicyMediator: Multi-Regional Policy Learning through Mediation Agents with Evolving Skills in OPC Ecosystems

    Oct 26, 2026Jie Li, Bin Guo, Georgina Curto +3Policy LearningPolicy Optimization

  12. Multiscale Policy Optimization for Long-Horizon LLM Agents

    Oct 26, 2026Tao Ren, Hui Yang, Jia Deng +16Policy OptimizationRL for LLM Agents

  13. When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning

    Oct 23, 2026Zongyao Zhao, Cheng-Jie Zhao, Ruihang Jiang +3Policy OptimizationGroup Relative Policy Optimization

  14. Dual-Adaptive Z-Score PPO: Dynamic Clipping Using Action Confidence and Normalized Advantage Magnitude

    Oct 23, 2026Taha M. Mahmoud, Naima KaabouchProximal Policy OptimizationPolicy Optimization

  15. MOER: Mix-Policy Optimization under Expert Prefix Guidance with Selective Rollback

    Oct 22, 2026Xuyang Zhong, Jiuding Yang, Yiwen Guo +1RL for Language Model ReasoningPolicy Optimization

  16. One Act, Many Masks: Effect-Marginal Policy Optimization for Long-Horizon Agents

    Oct 21, 2026Shaojin Ma, Ruitao Wang, Pengyi Li +6Policy OptimizationRL for LLM Agents

  17. Doob-Based Generative Policy Optimization

    Oct 20, 2026Maojiang Su, Qijie Zhu, Yu Xiao +4Policy OptimizationRL for Diffusion Models

  18. DR-APO: Decoupled-Representation Advantage-Guided Policy Optimization from Continuous Control to Embodied Navigation

    Oct 12, 2026Runhua Zhang, Yingjie Niu, Chao LiPolicy OptimizationRL for Generative Models

  19. Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence

    Oct 9, 2026Zhicheng Cai, Xinyuan Guo, Hanlin Wu +5RL for Language ModelsRL for Language Model Reasoning

  20. Closing the Horizon Gap in Policy Optimization for Adversarial MDPs

    Oct 8, 2026Mingyi Li, Taira TsuchiyaRegret Minimization in RLMarkov Decision Processes

  21. Pessimistic Minimax Learning for Public-Private Information Games under Unilateral Coverage

    Oct 4, 2026Shuze Daniel Liu, Claire Chen, Jiuqi Wang +1Imperfect-Information GamesZero-Sum Games

  22. On the Convergence of Success Conditioning for Policy Optimization

    Oct 2, 2026Matthew Brun, Xu Andy SunPolicy OptimizationMarkov Decision Processes

  23. Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds

    Oct 2, 2026Gabor Paczolay, Matteo Papini, Alberto Maria Metelli +2Policy GradientPolicy Gradient Methods

  24. FERPO: Forward Entropy-Regularized Policy Optimization

    Oct 1, 2026Sebastian Sanokowski, Alireza Sarmadi, Majid KhadivKL-Regularized RLPolicy Optimization

  25. Iterative Policy Refinement through Semantic Rollout Analysis

    Oct 1, 2026Feiyu Gavin Zhu, Qi Xu, Zhifei Deng +4Policy OptimizationLLM-Guided RL