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 1,827 篇，第 34 / 37 页

  1. ICLR 2023Does Zero-Shot Reinforcement Learning Exist?
  2. ICLR 2023Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
  3. ICLR 2023Efficient Deep Reinforcement Learning Requires Regulating Overfitting
  4. ICLR 2023Efficient Offline Policy Optimization with a Learned Model
  5. ICLR 2023Efficient Planning in a Compact Latent Action Space
  6. ICLR 2023Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
  7. ICLR 2023Emergence of Maps in the Memories of Blind Navigation Agents
  8. ICLR 2023ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation
  9. ICLR 2023ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret
  10. ICLR 2023EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model
  11. ICLR 2023Evaluating Long-Term Memory in 3D Mazes
  12. ICLR 2023Evolving Populations of Diverse RL Agents with MAP-Elites
  13. ICLR 2023Explaining RL Decisions with Trajectories
  14. ICLR 2023Extreme Q-Learning: MaxEnt RL without Entropy
  15. ICLR 2023Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems
  16. ICLR 2023Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
  17. ICLR 2023FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
  18. ICLR 2023From $t$-SNE to UMAP with contrastive learning
  19. ICLR 2023From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data
  20. ICLR 2023Generalize Learned Heuristics to Solve Large-scale Vehicle Routing Problems in Real-time
  21. ICLR 2023Generating Diverse Cooperative Agents by Learning Incompatible Policies
  22. ICLR 2023Generative Augmented Flow Networks
  23. ICLR 2023GFlowNets and variational inference
  24. ICLR 2023GoBigger: A Scalable Platform for Cooperative-Competitive Multi-Agent Interactive Simulation
  25. ICLR 2023Graph-based Deterministic Policy Gradient for Repetitive Combinatorial Optimization Problems
  26. ICLR 2023Gray-Box Gaussian Processes for Automated Reinforcement Learning
  27. ICLR 2023Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement
  28. ICLR 2023Guarded Policy Optimization with Imperfect Online Demonstrations
  29. ICLR 2023Guiding Safe Exploration with Weakest Preconditions
  30. ICLR 2023Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting
  31. ICLR 2023HiT-MDP: Learning the SMDP option framework on MDPs with Hidden Temporal Embeddings
  32. ICLR 2023Human-level Atari 200x faster
  33. ICLR 2023Hybrid RL: Using both offline and online data can make RL efficient
  34. ICLR 2023Hyper-Decision Transformer for Efficient Online Policy Adaptation
  35. ICLR 2023Hyperbolic Deep Reinforcement Learning
  36. ICLR 2023Imitating Graph-Based Planning with Goal-Conditioned Policies
  37. ICLR 2023Impossibly Good Experts and How to Follow Them
  38. ICLR 2023Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs
  39. ICLR 2023Improving Deep Policy Gradients with Value Function Search
  40. ICLR 2023In-context Reinforcement Learning with Algorithm Distillation
  41. ICLR 2023In-sample Actor Critic for Offline Reinforcement Learning
  42. ICLR 2023Interaction-Based Disentanglement of Entities for Object-Centric World Models
  43. ICLR 2023Investigating Multi-task Pretraining and Generalization in Reinforcement Learning
  44. ICLR 2023Is Conditional Generative Modeling all you need for Decision Making?
  45. ICLR 2023Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function
  46. ICLR 2023Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
  47. ICLR 2023Latent State Marginalization as a Low-cost Approach for Improving Exploration
  48. ICLR 2023Latent Variable Representation for Reinforcement Learning
  49. ICLR 2023Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
  50. ICLR 2023Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering

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。