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 1,190 篇，第 5 / 24 页
- ICLR 2024Learning Multi-Agent Communication from Graph Modeling Perspective
- ICLR 2024Learning Multi-Agent Communication with Contrastive Learning
- ICLR 2024Learning Nash Equilibria in Rank-1 Games
- ICLR 2024Learning to Act from Actionless Videos through Dense Correspondences
- ICLR 2024Learning to Act without Actions
- ICLR 2024Learning to Make Adherence-aware Advice
- ICLR 2024Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models
- ICLR 2024Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation
- ICLR 2024Local Search GFlowNets
- ICLR 2024Locality Sensitive Sparse Encoding for Learning World Models Online
- ICLR 2024LOQA: Learning with Opponent Q-Learning Awareness
- ICLR 2024Making RL with Preference-based Feedback Efficient via Randomization
- ICLR 2024MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
- ICLR 2024Massively Scalable Inverse Reinforcement Learning in Google Maps
- ICLR 2024Mastering Memory Tasks with World Models
- ICLR 2024Maximum Entropy Heterogeneous-Agent Reinforcement Learning
- ICLR 2024Maximum Entropy Model Correction in Reinforcement Learning
- ICLR 2024Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
- ICLR 2024Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization Analysis
- ICLR 2024Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer
- ICLR 2024METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
- ICLR 2024MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
- ICLR 2024Motif: Intrinsic Motivation from Artificial Intelligence Feedback
- ICLR 2024Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
- ICLR 2024Multimodal Web Navigation with Instruction-Finetuned Foundation Models
- ICLR 2024Negatively Correlated Ensemble Reinforcement Learning for Online Diverse Game Level Generation
- ICLR 2024ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update
- ICLR 2024Off-Policy Primal-Dual Safe Reinforcement Learning
- ICLR 2024Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
- ICLR 2024Offline RL with Observation Histories: Analyzing and Improving Sample Complexity
- ICLR 2024OMNI: Open-endedness via Models of human Notions of Interestingness
- ICLR 2024On Double Descent in Reinforcement Learning with LSTD and Random Features
- ICLR 2024On Representation Complexity of Model-based and Model-free Reinforcement Learning
- ICLR 2024On Stationary Point Convergence of PPO-Clip
- ICLR 2024On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning
- ICLR 2024On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning
- ICLR 2024On the Joint Interaction of Models, Data, and Features
- ICLR 2024On the Role of General Function Approximation in Offline Reinforcement Learning
- ICLR 2024On Trajectory Augmentations for Off-Policy Evaluation
- ICLR 2024On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- ICLR 2024Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
- ICLR 2024OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
- ICLR 2024Optimal Sample Complexity for Average Reward Markov Decision Processes
- ICLR 2024PAE: Reinforcement Learning from External Knowledge for Efficient Exploration
- ICLR 2024PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
- ICLR 2024Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
- ICLR 2024Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings
- ICLR 2024Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning
- ICLR 2024PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation
- ICLR 2024Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
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。