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
- 强化学习论文从 2023 年的 1,070 篇增长到 2026 年的 2,985 篇，三年间扩大到约 2.8 倍。
- NeurIPS 是发强化学习论文最多的会议，2023–2026 年共 2,494 篇，占四个会议总量的 36%。
- 交叉方向里涨得最快的是推理模型：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 437 篇。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 484 | 233 | 297 | 56 | 1,070 |
| 2024 | 466 | 304 | 356 | 64 | 1,190 |
| 2025 | 784 | 379 | 405 | 72 | 1,640 |
| 2026 | 760 | 911 | 1,021 | 293 | 2,985 |
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
- NeurIPS 2026\texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
- ICML 2026$\text{DT}^\text{2}$: Decision-Targeted Digital Twins
- ICLR 2026$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Textual Space
- CVPR 2026A Causal Marriage between VLM and IRM from Understanding to
- NeurIPS 2025$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
- ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
- ICLR 2025$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee
- CVPR 2025All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising
- NeurIPS 2024A Critical Evaluation of AI Feedback for Aligning Large Language Models
- ICML 2024${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
- ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
- CVPR 2024DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning
- NeurIPS 2023“Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization
- ICML 2023A Connection between One-Step RL and Critic Regularization in Reinforcement Learning
- ICLR 2023$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games
- CVPR 2023"Seeing" Electric Network Frequency From Events
- NeurIPS 2026$\varphi$TD: Distributional Reinforcement Learning using Characteristic Functions
- ICML 2026$\textit{S}$-SPPO: Semantic-Calibrated Self-Play Preference Optimization
- ICLR 2026$AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning
- CVPR 2026AdaptVision Efficient Vision-Language Models via Adaptive Visual Acquisition
全部强化学习论文
共 6,885 篇，第 122 / 138 页
- ICLR 2023Represent to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency
- ICLR 2023Representation Learning for Low-rank General-sum Markov Games
- ICLR 2023ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor
- ICLR 2023Revisiting Intrinsic Reward for Exploration in Procedurally Generated Environments
- ICLR 2023Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching
- ICLR 2023Reward Design with Language Models
- ICLR 2023Risk-Aware Reinforcement Learning with Coherent Risk Measures and Non-linear Function Approximation
- ICLR 2023RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
- ICLR 2023ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs
- ICLR 2023RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning
- ICLR 2023Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-Free RL
- ICLR 2023Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation
- ICLR 2023Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks
- ICLR 2023Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier
- ICLR 2023Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing
- ICLR 2023Scaling Laws for a Multi-Agent Reinforcement Learning Model
- ICLR 2023Scaling Pareto-Efficient Decision Making via Offline Multi-Objective RL
- ICLR 2023Simple Emergent Action Representations from Multi-Task Policy Training
- ICLR 2023Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective
- ICLR 2023SMART: Self-supervised Multi-task pretrAining with contRol Transformers
- ICLR 2023Solving Continuous Control via Q-learning
- ICLR 2023Spectral Decomposition Representation for Reinforcement Learning
- ICLR 2023SpeedyZero: Mastering Atari with Limited Data and Time
- ICLR 2023Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
- ICLR 2023Statistical Efficiency of Score Matching: The View from Isoperimetry
- ICLR 2023Stay Moral and Explore: Learn to Behave Morally in Text-based Games
- ICLR 2023Systematic Rectification of Language Models via Dead-end Analysis
- ICLR 2023Task Ambiguity in Humans and Language Models
- ICLR 2023TEMPERA: Test-Time Prompt Editing via Reinforcement Learning
- ICLR 2023Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning
- ICLR 2023The In-Sample Softmax for Offline Reinforcement Learning
- ICLR 2023The Power of Regularization in Solving Extensive-Form Games
- ICLR 2023The Provable Benefit of Unsupervised Data Sharing for Offline Reinforcement Learning
- ICLR 2023The Role of Coverage in Online Reinforcement Learning
- ICLR 2023The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
- ICLR 2023Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints
- ICLR 2023Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
- ICLR 2023Towards Interpretable Deep Reinforcement Learning with Human-Friendly Prototypes
- ICLR 2023Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs
- ICLR 2023Transformer-based model for symbolic regression via joint supervised learning
- ICLR 2023Transformer-based World Models Are Happy With 100k Interactions
- ICLR 2023Transformers are Sample-Efficient World Models
- ICLR 2023Truthful Self-Play
- ICLR 2023Understanding and Adopting Rational Behavior by Bellman Score Estimation
- ICLR 2023User-Interactive Offline Reinforcement Learning
- ICLR 2023Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning
- ICLR 2023Variational Information Pursuit for Interpretable Predictions
- ICLR 2023Variational Latent Branching Model for Off-Policy Evaluation
- ICLR 2023VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
- ICLR 2023VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation
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"}
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。