RL Exploration

RL: Reinforcement Learning

Overview

Exploration studies how an agent can gather useful experience when rewards are sparse, the environment is uncertain, or its current policy visits only a narrow part of the state space. Common approaches use uncertainty bonuses, novelty and entropy rewards, model-based planning, goal or skill discovery, memory, and structured or language-guided exploration. These ideas are tested in settings from bandits and sparse-reward navigation to robotics, multi-agent tasks, and language-model reasoning and tool use. A central challenge is to seek information that improves future decisions without wasting experience on irrelevant novelty or destabilizing learning, while maintaining safety and useful behavior.

Latest papers

CardsList

234 papers15 papers in the last four weeks, down 53% on the four weeks before. 0.1% of all new papers.

  1. MCTS Is Counting the Wrong Thing: Learning Exploration Counts for LLM Reasoning

    Nov 17, 2026Xuan Zhang, Zhijian Zhou, Zicheng Hu +4Monte Carlo Tree SearchRL for Language Model Reasoning

  2. What Makes a Good Move? Learning to Act from Experience in Visual Worlds

    Nov 16, 2026Cehao Yang, Ziyi He, Jing Yi +2Policy LearningVisual RL

  3. Random Exploration is Random

    Nov 12, 2026Yingkang Luo, Hua-Dong Xiong, Hanbo Xie +5Human Behavior ModelingExploration-Exploitation Tradeoff

  4. The Illusion of Diversity: Aligning LLM Exploration via Effective Entropy

    Nov 11, 2026Xiaoliang Fu, Jiaye Lin, Yangyi Fang +4RL for Language Model ReasoningRL Exploration

  5. Fade to... Red? Scheduling Coloured Noise Exploration Supports Efficient Robot Learning with Reduced Movement Jerk

    Nov 9, 2026Francisco M. López, Francisco CruzRL ExplorationRobotic RL

  6. Sampling Is Not Curiosity: Why LLM Agents Should Investigate

    Nov 7, 2026Alfonso Amayuelas, Piotr Piękos, Xin Eric Wang +3LLM AgentsIntrinsic Motivation

  7. Q-OIL: Optimistic Exploration in Learning from Human Interventions

    Nov 5, 2026Pranav Teegavarapu, Sriyash Poddar, Rico Qi +5RL for RoboticsHuman-in-the-Loop AI

  8. Bridging Neural Tangent Kernel Analysis and Reinforcement Learning for Deep Function Approximation

    Nov 2, 2026William St-Arnaud, Margarida Carvalho, Golnoosh FarnadiNeural Tangent KernelNeural Network Training Dynamics

  9. When Does Exploration Prevent Collapse? Three Regimes and the Path of the Reward in Self-Consistency Training

    Oct 31, 2026Jaeho Hwang, Uiwon HwangTest-Time RLRL Exploration

  10. Guided-RLVR: Guided Exploration in Reinforcement Learning with Verifiable Rewards

    Oct 27, 2026Bo Yang, Zishuai Zhang, Weihua Li +3RL for Language Model ReasoningReinforcement Learning with Verifiable Rewards

  11. Multi-Horizon Future Discovery for Physics-Informed Exploration

    Oct 26, 2026Shuwei Wang, Qiang Guan, Brian Qiu +5RL ExplorationIntrinsic Motivation

  12. VISTA: Active Exploration for Self-Improvement in Embodied Agents

    Oct 26, 2026Zhang Zhang, Shengjun Zhang, Simin Huang +4Self-Improving AgentsAgent Harness Optimization

  13. Asymmetric On-Policy Distillation Learns In-Context Exploration

    Oct 21, 2026Sriyash Poddar, Yanda Bao, Jacob Krantz +5RL ExplorationPartially Observable RL

  14. Second Thoughts: Exploring and Planning through Comparative Imagination in World Models

    Oct 20, 2026Hieu Tran, Hong YuWorld Model-Based PlanningModel-Based RL

  15. Activation-Space Exploration for Visual and Textual Reasoning with RLVR

    Oct 19, 2026Yunan Zeng, Jinhao Jing, Xi Cheng +1RL for Language Model ReasoningRL Exploration

  16. Productive State-Space Exploration for Multi-turn RL in LLM Agents

    Oct 19, 2026Mohammed Haroon Dupty, Yong Liang Goh, Song Guo +1RL for LLM AgentsRL Exploration

  17. Measuring Empowerment from Offline Data for Intrinsically Motivated Exploration

    Oct 17, 2026Ishir Garg, Vivek Myers, Qiyang Li +3EmpowermentRL Exploration

  18. What Information Buys in Active Inference

    Oct 13, 2026Melih Kandemir, Mustafa Mert ÇelikokRL ExplorationActive Inference

  19. Explore with Memory, Learn without It: In-Context Exploration and Self-Distillation for LLM Reasoning

    Oct 13, 2026Yutong Chen, Zhichao Xu, Rui Liu +1RL for Language Model ReasoningRL Exploration

  20. MemAct: Streaming Spatial Understanding with Memory and Active Exploration

    Oct 13, 2026Yuxi Wei, Wei Huang, Qirui Chen +2Memory-Augmented AgentsEmbodied Reasoning

  21. CFG-Policy: Unified Diffusion Policy Learning Framework via Classifier-free Guidance

    Oct 10, 2026Shutong Ding, Zhaoyang Liu, Yimiao Zhou +3Diffusion PolicyRobotic RL

  22. Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents

    Oct 9, 2026Ziang Ye, Wentao Shi, Lei Chen +7Long-Horizon LLM AgentsLLM Agent Planning

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

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

  24. Decoupling Exploration from Optimization in RLVR

    Oct 7, 2026Saif Punjwani, Micah GoldblumRL for Language Model ReasoningRL Exploration

  25. Constraint Tree Exploration for Learning from Language Feedback

    Oct 6, 2026Shaoang Li, Daniel R. Jiang, Jian LiError FeedbackRL Exploration

  26. Variance-Aware Fine-Grained Gap-Dependent Bounds for Online Reinforcement Learning

    Oct 3, 2026Haochen Zhang, Lingzhou Xue, Zhong ZhengReinforcement LearningModel-Free RL