Sample-Efficient RL

RL: Reinforcement Learning

Ask about this topic

Overview

Sample-efficient reinforcement learning aims to reduce the experience needed to learn useful policies, especially when interaction is slow, costly, or risky. Common approaches improve exploration with optimism or uncertainty estimates, reuse data through replay and demonstrations, learn models for planning, or exploit structure such as hierarchy, symmetry, and known dynamics. These methods are studied in settings from tabular and robust decision processes to MuJoCo and Atari control, robotics, and language-model training with verifiable rewards. The field balances empirical gains and PAC or regret guarantees against challenges such as stale replay, model error, limited data coverage, and differences between sample counts and wall-clock cost.

Latest papers

CardsList

253 papers30 papers in the last four weeks, up 150% on the four weeks before. 0.2% of all new papers.

  1. Safe Multi-Objective Reinforcement Learning: Zero Constraint Violation and Primal-Averaging Convergence

    Oct 29, 2026Chenxi Li, Yao Shu, Siyang Gao +2Multi-Objective Reinforcement LearningReinforcement Learning

    Harbin Institute of Technology, Harbin, Heilongjiang, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China · City University of Hong Kong, Hong Kong, China

  2. Echo: Scaling Visual Reinforcement Learning with Off-policy Experience

    Oct 27, 2026Gagan KhandateVisual RLRobotic RL

  3. EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning

    Oct 27, 2026Sihan Yang, Weichen Bai, Ruichuan An +9Agentic RLReinforcement Learning

    PKU · XJTU · THU +3

  4. Provably Efficient Q-learning for Robust Reinforcement Learning

    Oct 26, 2026Yuchen Jiao, Gen LiRobust RLDistributionally Robust RL

    Department of Statistics and Data Science, Chinese University of Hong Kong.

  5. SAFTER: Safety-Aware Filtering Through Explicit Recoverability for Robust Reinforcement Learning under Distribution Shift

    Oct 21, 2026Benedictus C. G. Cinun, Bin HuSafe RLReinforcement Learning

    Department of Electrical and Computer Engineering, University of Houston, Houston, TX 77004, USA · Department of Engineering Technology, University of Houston, Houston, TX 77004, USA

  6. Ask to Learn: Query-Based Collaborative Reinforcement Learning

    Oct 20, 2026Kaicheng Zhang, Hongqian Niu, Laixi Shi +3Reinforcement LearningSample-Efficient RL

    University of North Carolina at Chapel Hill · Johns Hopkins University · Carnegie Mellon University

  7. Adaptive Decoding Methods for Token-Efficient Reinforcement Learning

    Oct 19, 2026Zhaonan Li, Zelei Cheng, Amritansh Mishra +5Sample-Efficient RLReinforcement Learning with Verifiable Rewards

    School of Computing and Augmented Intelligence Arizona State University · AI Foundations Capital One

  8. Follow the Mixed Groups: Ridge-Tracking Gaussian Sampling for Zero-Variance Web Rollouts

    Oct 18, 2026Tomas Duncun, Jonah Ellison, Owen Pell +4Adaptive SamplingSample-Efficient RL

    University of Michigan Ann Arbor, Michigan, USA · University of Edinburgh Edinburgh, United Kingdom

  9. Sample-Efficient Reinforcement Learning with General Utilities via Neural Dual Critics

    Oct 17, 2026Ankur Naskar, Vaneet AggarwalReinforcement LearningSample-Efficient RL

    Indian Institute of Science, India · Purdue University, USA

  10. Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors

    Oct 16, 2026Carl Qi, Weijun Dong, Xiaojie Wang +8Robot Policy LearningRobotic RL

    Amazon · UT Austin · UC San Diego +2

  11. Co-Evolving Acting and Forecasting for Language Agents

    Oct 14, 2026Haofei Yu, Yixing Chen, Yining Zhao +6RL for LLM AgentsAgentic RL

    University of Illinois Urbana-Champaign · University of California San Diego · Meta AI

  12. Average-Reward Policy Identification from a Single Continuing Trajectory

    Oct 14, 2026Tongxi WangReinforcement LearningAverage-Reward RL

    Southeast University

  13. Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards

    Oct 13, 2026Yuante Li, Junwei Quan, Kai Qiu +2Reinforcement LearningReinforcement Learning with Verifiable Rewards

    Carnegie Mellon University · University of Toronto

  14. Fast Rates for Offline Q-Learning with KL Regularization

    Oct 13, 2026Yize Hao, Guangxin Jiang, Shuang QiuOffline RLQ-Learning

    Harbin Institute of Technology. · City University of Hong Kong.

  15. Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling

    Oct 10, 2026Jiarong Wen, Qi Tao, Kaiyu Zhang +5Sample-Efficient RLRL Post-Training

    College of Science, National University of Defense Technology · Department of Automation, Tsinghua University

  16. Variance-Reduced Policy Gradient is Nearly Minimax-Optimal

    Oct 9, 2026Leonardo Cesani, Matteo Papini, Marcello RestelliPolicy GradientPolicy Gradient Methods

    Politecnico di Milano · Universit`a degli Studi di Milano

  17. Can Jev be Your Q or Policy in Reinforcement Learning?

    Oct 8, 2026Yi Ma, Tianpei Yang, Yaodong Yang +2LLM-Guided RLSample-Efficient RL

    Shanxi University · Nanjing University · The Chinese University of Hong Kong +2

  18. A Closed-Loop Non-Asymptotic Convergence Analysis of PPO with Learned Critics and Clipping

    Oct 7, 2026Junwei Su, Mengfan Liu, Yanyong Zhang +1Proximal Policy OptimizationActor-Critic Methods

    School of Artificial Intelligence and Data Science, University of Science and Technology of China · Department of Computer Science, University of Hong Kong

  19. Sample-Efficiency of Kolmogorov-Arnold Networks

    Oct 7, 2026Kevin Riehl, Shaimaa K. El-Baklish, Fan Wu +1Kolmogorov-Arnold NetworksSample-Efficient RL

    ETH Zürich, IVT & Agentic Systems Lab (ASL) · ETH Zürich, IVT · ETH Zürich, Agentic Systems Lab (ASL)

  20. Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense

    Oct 7, 2026Fernando Martinez, Abhishek Satyam, Tao Li +3Autonomous Cyber DefenseLLM-Guided RL

    Department of Computer and Information Sciences, Fordham University, New York, USA · Department of Systems Engineering, Stevens Institute of Technology, New Jersey, USA

  21. Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning

    Oct 5, 2026Daniele Affinita, Ming Xu, Rudolf Reiter +2Sample-Efficient RL

    EPFL, Switzerland · University of Zurich, Switzerland

  22. Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model

    Oct 3, 2026Amirparsa Bahrami, Oliver Mortensen, Mohammad Sadegh TalebiRisk-Sensitive RLSample-Efficient RL

    School of Electrical Engineering, Sharif University of Technology · Department of Computer Science, University of Copenhagen

  23. Sharp Convergence and Sample Complexity of Policy Mirror Descent for Average-Reward MDPs

    Oct 2, 2026Enes Arda, Atilla EryilmazMarkov Decision ProcessesAverage-Reward RL

    The Ohio State University

  24. 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

    Politecnico di Milano. · Budapest University of Technology and Economics. · University of Milan.

  25. Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning

    Oct 1, 2026Xinjie Liu, Ruihan Zhao, Anirban Chaudhuri +3Policy Gradient MethodsPolicy Learning

    University of Texas at Austin · University of British Columbia

  26. Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help?

    Oct 1, 2026Alessandro Montenegro, Riccardo Venturelli, Marco Mussi +2Experience ReplayProximal Policy Optimization

    Politecnico di Milano, Milan, Italy · Università degli Studi di Milano, Milan, Italy

  27. OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search

    Sep 30, 2026Junyu Lu, Shichao Weng, Zhiqiang Wang +10Tree SearchPolicy Gradient Methods

    Dobot Robotics · Independent Researcher · Zhejiang University +2

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

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

    School of Mathematical Sciences, Fudan University · School of Data Science, Fudan University

  29. Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse

    Sep 30, 2026Nima H. SiboniImportance SamplingProximal Policy Optimization

    Juna.ai, Kastanienallee 32, 10435 Berlin, Germany

  30. Prompts Live on an Arc: Gaussian Curricula in Fisher--Rao Coordinates for Rollout-Efficient GRPO

    Sep 29, 2026Mei Okonkwo, Pixel Nomand, Julian Berg +5Prompt Selection for RLGroup Relative Policy Optimization

    University of Wisconsin–Madison · University of Washington