强化学习论文趋势 2023–2026

策略优化、离线 RL 与基于环境的决策学习

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 6,885 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

强化学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023484233297561,070
2024466304356641,190
2025784379405721,640
20267609111,0212932,985

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部强化学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 379 篇，第 6 / 8 页

  1. ICLR 2025Open-World Reinforcement Learning over Long Short-Term Imagination
  2. ICLR 2025Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Processes
  3. ICLR 2025Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization
  4. ICLR 2025Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization
  5. ICLR 2025OptionZero: Planning with Learned Options
  6. ICLR 2025ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization
  7. ICLR 2025Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control
  8. ICLR 2025OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination
  9. ICLR 2025PABBO: Preferential Amortized Black-Box Optimization
  10. ICLR 2025Pareto Prompt Optimization
  11. ICLR 2025PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning
  12. ICLR 2025PersonalLLM: Tailoring LLMs to Individual Preferences
  13. ICLR 2025PN-GAIL: Leveraging Non-optimal Information from Imperfect Demonstrations
  14. ICLR 2025POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding
  15. ICLR 2025Policy Optimization under Imperfect Human Interactions with Agent-Gated Shared Autonomy
  16. ICLR 2025PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial Optimization
  17. ICLR 2025Post-hoc Reward Calibration: A Case Study on Length Bias
  18. ICLR 2025Preference Elicitation for Offline Reinforcement Learning
  19. ICLR 2025Preference Optimization for Reasoning with Pseudo Feedback
  20. ICLR 2025Prevalence of Negative Transfer in Continual Reinforcement Learning: Analyses and a Simple Baseline
  21. ICLR 2025Prioritized Generative Replay
  22. ICLR 2025Procedural Synthesis of Synthesizable Molecules
  23. ICLR 2025Process Reward Model with Q-value Rankings
  24. ICLR 2025PWM: Policy Learning with Multi-Task World Models
  25. ICLR 2025Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
  26. ICLR 2025Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
  27. ICLR 2025QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing
  28. ICLR 2025RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization
  29. ICLR 2025Rapidly Adapting Policies to the Real-World via Simulation-Guided Fine-Tuning
  30. ICLR 2025Reconstruction-Guided Policy: Enhancing Decision-Making through Agent-Wise State Consistency
  31. ICLR 2025REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments
  32. ICLR 2025Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
  33. ICLR 2025Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator
  34. ICLR 2025Regret-Optimal List Replicable Bandit Learning: Matching Upper and Lower Bounds
  35. ICLR 2025Regulatory DNA Sequence Design with Reinforcement Learning
  36. ICLR 2025Reinforcement Learning for Control of Non-Markovian Cellular Population Dynamics
  37. ICLR 2025Reinforcement Learning from Imperfect Corrective Actions and Proxy Rewards
  38. ICLR 2025Reinforcement learning with combinatorial actions for coupled restless bandits
  39. ICLR 2025Residual Kernel Policy Network: Enhancing Stability and Robustness in RKHS-Based Reinforcement Learning
  40. ICLR 2025Residual-MPPI: Online Policy Customization for Continuous Control
  41. ICLR 2025Rethinking Light Decoder-based Solvers for Vehicle Routing Problems
  42. ICLR 2025Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?
  43. ICLR 2025Revisiting a Design Choice in Gradient Temporal Difference Learning
  44. ICLR 2025REvolve: Reward Evolution with Large Language Models using Human Feedback
  45. ICLR 2025Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning
  46. ICLR 2025Reward Learning from Multiple Feedback Types
  47. ICLR 2025Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
  48. ICLR 2025Risk-Sensitive Variational Actor-Critic: A Model-Based Approach
  49. ICLR 2025RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
  50. ICLR 2025Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查强化学习在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "reinforcement-learning"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇强化学习论文？
共 6,885 篇，按年份分别是 2023 年 1,070 篇、2024 年 1,190 篇、2025 年 1,640 篇、2026 年 2,985 篇。
NeurIPS 2026 有多少篇强化学习论文？
NeurIPS 2026 有 760 篇强化学习论文，上一届是 784 篇。
ICLR 2026 有多少篇强化学习论文？
ICLR 2026 有 911 篇强化学习论文，上一届是 379 篇。
ICML 2026 有多少篇强化学习论文？
ICML 2026 有 1,021 篇强化学习论文，上一届是 405 篇。
CVPR 2026 有多少篇强化学习论文？
CVPR 2026 有 293 篇强化学习论文，上一届是 72 篇。
哪个会议的强化学习论文最多？
NeurIPS，2023–2026 年共 2,494 篇。