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 6,885 篇，第 120 / 138 页

  1. ICLR 2023GoBigger: A Scalable Platform for Cooperative-Competitive Multi-Agent Interactive Simulation
  2. ICLR 2023Graph-based Deterministic Policy Gradient for Repetitive Combinatorial Optimization Problems
  3. ICLR 2023Gray-Box Gaussian Processes for Automated Reinforcement Learning
  4. ICLR 2023Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement
  5. ICLR 2023Guarded Policy Optimization with Imperfect Online Demonstrations
  6. ICLR 2023Guiding Safe Exploration with Weakest Preconditions
  7. ICLR 2023Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting
  8. ICLR 2023HiT-MDP: Learning the SMDP option framework on MDPs with Hidden Temporal Embeddings
  9. ICLR 2023Human-level Atari 200x faster
  10. ICLR 2023Hybrid RL: Using both offline and online data can make RL efficient
  11. ICLR 2023Hyper-Decision Transformer for Efficient Online Policy Adaptation
  12. ICLR 2023Hyperbolic Deep Reinforcement Learning
  13. ICLR 2023Imitating Graph-Based Planning with Goal-Conditioned Policies
  14. ICLR 2023Impossibly Good Experts and How to Follow Them
  15. ICLR 2023Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs
  16. ICLR 2023Improving Deep Policy Gradients with Value Function Search
  17. ICLR 2023In-context Reinforcement Learning with Algorithm Distillation
  18. ICLR 2023In-sample Actor Critic for Offline Reinforcement Learning
  19. ICLR 2023Interaction-Based Disentanglement of Entities for Object-Centric World Models
  20. ICLR 2023Investigating Multi-task Pretraining and Generalization in Reinforcement Learning
  21. ICLR 2023Is Conditional Generative Modeling all you need for Decision Making?
  22. ICLR 2023Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function
  23. ICLR 2023Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
  24. ICLR 2023Latent State Marginalization as a Low-cost Approach for Improving Exploration
  25. ICLR 2023Latent Variable Representation for Reinforcement Learning
  26. ICLR 2023Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
  27. ICLR 2023Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering
  28. ICLR 2023Learning About Progress From Experts
  29. ICLR 2023Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward
  30. ICLR 2023Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition
  31. ICLR 2023Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model
  32. ICLR 2023Learning Simultaneous Navigation and Construction in Grid Worlds
  33. ICLR 2023Learning Soft Constraints From Constrained Expert Demonstrations
  34. ICLR 2023Learning to Segment from Noisy Annotations: A Spatial Correction Approach
  35. ICLR 2023Learning Uncertainty for Unknown Domains with Zero-Target-Assumption
  36. ICLR 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
  37. ICLR 2023Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies
  38. ICLR 2023LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning
  39. ICLR 2023MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection
  40. ICLR 2023MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
  41. ICLR 2023Making Better Decision by Directly Planning in Continuous Control
  42. ICLR 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
  43. ICLR 2023Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning
  44. ICLR 2023Memory Gym: Partially Observable Challenges to Memory-Based Agents
  45. ICLR 2023Mind the Gap: Offline Policy Optimization for Imperfect Rewards
  46. ICLR 2023Minimax Optimal Kernel Operator Learning via Multilevel Training
  47. ICLR 2023Minimum Description Length Control
  48. ICLR 2023Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach
  49. ICLR 2023MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
  50. ICLR 2023More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization

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。