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 45% on the four weeks before. 0.1% of all new papers.

  1. Towards Optimal Policy Improvement

    Oct 1, 2026Yaniv Oren, Viliam Vadocz, Wiktor Zabka +7Markov Decision ProcessesPolicy Optimization

  2. Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting

    Oct 1, 2026Aditya Dubey, Namah Gupta, Vinti AgarwalRL for Language ModelsLarge Language Model-Guided Optimization

  3. Role-Adaptive Policy Optimization for Offline Reinforcement Learning

    Sep 30, 2026Seonvin Cho, Soohyun Choi, Songnam HongPolicy OptimizationOffline RL

  4. Fast Regularized Policy Mirror Descent with One-Step TD Updates

    Sep 30, 2026Qipei Chen, Wenye Li, Yule Sun +1Markov Decision ProcessesPolicy Optimization

  5. Self-Evolving Algorithm-Design Agents: Escaping In-Context Evolutionary Stagnation via Population-Curated Policy Optimization

    Sep 30, 2026Chen Lu, Ke Xue, Siyuan Xu +2Automated Algorithm DiscoveryLarge Language Model-Guided Optimization

  6. Achieving an O(1/N)O(1/N) Optimality Gap in Average-Reward Weakly-Coupled MDPs

    Sep 29, 2026Yige Hong, Xiangcheng Zhang, Qiaomin Xie +2Markov Decision ProcessesAverage-Reward RL

  7. Towards Better Training Signal: Advantage Clipped Policy Optimization

    Sep 29, 2026Ruichuan Huang, Jinghan Liu, Congliang ChenPolicy OptimizationRL for Language Model Reasoning

  8. Regularized policy gradient with learned mixtures of Gaussians for games with continuous actions

    Sep 29, 2026Ondřej Kubíček, Viliam Lisý, Tuomas SandholmGame-Playing AgentsSelf-Play RL

  9. Factorized Scheduling Principle: Learning Interpretable and Transferable Policies via Structured Additive Functions

    Sep 29, 2026Hong Je-Gal, Hyun-Suk LeeInterpretable MLPolicy Optimization

  10. RareDx: Controlled Knowledge Integration and Graph-Grounded Policy Optimization for Rare-Disease Diagnosis

    Sep 28, 2026Bo Zhang, Yuchen Wang, Dongbai Li +6Rare Disease DiagnosisLLM Reasoning with Graphs

  11. ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning

    Sep 28, 2026Yihang Chen, Yuanhao Ban, Cho-Jui HsiehPolicy OptimizationReinforcement Learning with Verifiable Rewards

  12. Proactive Dialogue Policy Optimization via Cognitive-State Transition

    Sep 28, 2026Minghui Ma, Mengqi Chen, Bin Guo +1Policy OptimizationConversational Agents

  13. Vanilla Policy Optimization Is Both Optimal and Differentially Private for Stochastic Contextual Bandits

    Sep 27, 2026Idan Attias, Orin Levy, Alexander Ryabchenko +2Policy OptimizationDifferential Privacy

  14. NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents

    Sep 27, 2026Xu Liu, WenZhang Wei, Jun Cao +4Continual Learning for LLM AgentsPolicy Optimization

  15. Learnable Randomization as Commitment Against Adaptive Optimizers

    Sep 26, 2026Zihan Deng, Chuanzhi Xu, Xiaozhen Zhong +2Policy OptimizationStackelberg Games

  16. Action Shaping: Policies Absorb What They Can Express

    Sep 26, 2026Yanjun Chen, Jinghan Wang, Xiaoyu Shen +2Policy OptimizationPolicy Learning

  17. G2MAF: Test-Time Gradient Guidance for Multi-Agent Flow Policies

    Sep 25, 2026Guowei Zou, Haitao Wang, Guoxin Wang +4Cooperative MARLTest-Time RL

  18. PolicyAttention: Softmax Attention Implements Policy Mirror Descent for Closed-Loop Control

    Sep 24, 2026Yuhe Sui, Yingzhi Tang, Shufang ChenPolicy LearningPolicy Optimization

  19. Learning When to Refine: Long-Horizon Reinforcement Learning for Budgeted Neural-Operator PDE Solvers

    Sep 19, 2026Ange TongReinforcement LearningNeural Operators

  20. Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control

    Sep 17, 2026Yilang Liu, Haoxiang You, Qian Wang +2Policy OptimizationVisuomotor Policy Learning

  21. Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization

    Sep 17, 2026Yingxuan Zhuang, Binhe Yu, Jingxiao Yang +6Group Relative Policy OptimizationPolicy Optimization

  22. Bellman Policy Optimization

    Sep 14, 2026Zhuoqing Song, Haotian Xu, Xikun Zhang +1Reinforcement LearningRL for Language Model Reasoning

  23. Refinement-Based Flow Policy Optimization

    Sep 14, 2026Bumgeun Park, Hyukjun Yang, Donghwan LeeRL ControlFlow Matching

  24. Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection

    Sep 9, 2026Haoyue Liu, Xiaoyu Ma, Ye Chen +2RL for Language Model ReasoningGroup Relative Policy Optimization