强化学习论文趋势 2023–2026

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。

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 304 篇，第 4 / 7 页

151. ICLR 2024Mastering Memory Tasks with World Models
152. ICLR 2024Maximum Entropy Heterogeneous-Agent Reinforcement Learning
153. ICLR 2024Maximum Entropy Model Correction in Reinforcement Learning
154. ICLR 2024Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
155. ICLR 2024Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization Analysis
156. ICLR 2024Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer
157. ICLR 2024METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
158. ICLR 2024MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
159. ICLR 2024Motif: Intrinsic Motivation from Artificial Intelligence Feedback
160. ICLR 2024Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
161. ICLR 2024Multimodal Web Navigation with Instruction-Finetuned Foundation Models
162. ICLR 2024Negatively Correlated Ensemble Reinforcement Learning for Online Diverse Game Level Generation
163. ICLR 2024ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update
164. ICLR 2024Off-Policy Primal-Dual Safe Reinforcement Learning
165. ICLR 2024Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
166. ICLR 2024Offline RL with Observation Histories: Analyzing and Improving Sample Complexity
167. ICLR 2024OMNI: Open-endedness via Models of human Notions of Interestingness
168. ICLR 2024On Double Descent in Reinforcement Learning with LSTD and Random Features
169. ICLR 2024On Representation Complexity of Model-based and Model-free Reinforcement Learning
170. ICLR 2024On Stationary Point Convergence of PPO-Clip
171. ICLR 2024On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning
172. ICLR 2024On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning
173. ICLR 2024On the Joint Interaction of Models, Data, and Features
174. ICLR 2024On the Role of General Function Approximation in Offline Reinforcement Learning
175. ICLR 2024On Trajectory Augmentations for Off-Policy Evaluation
176. ICLR 2024On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
177. ICLR 2024Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
178. ICLR 2024OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
179. ICLR 2024Optimal Sample Complexity for Average Reward Markov Decision Processes
180. ICLR 2024PAE: Reinforcement Learning from External Knowledge for Efficient Exploration
181. ICLR 2024PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
182. ICLR 2024Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
183. ICLR 2024Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings
184. ICLR 2024Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning
185. ICLR 2024PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation
186. ICLR 2024Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
187. ICLR 2024Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents
188. ICLR 2024Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning
189. ICLR 2024Pre-Training and Fine-Tuning Generative Flow Networks
190. ICLR 2024Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning
191. ICLR 2024Pre-training with Synthetic Data Helps Offline Reinforcement Learning
192. ICLR 2024Predictive auxiliary objectives in deep RL mimic learning in the brain
193. ICLR 2024Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning
194. ICLR 2024Privately Aligning Language Models with Reinforcement Learning
195. ICLR 2024Privileged Sensing Scaffolds Reinforcement Learning
196. ICLR 2024Proper Laplacian Representation Learning
197. ICLR 2024Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
198. ICLR 2024Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes
199. ICLR 2024Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
200. ICLR 2024Provable Offline Preference-Based 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。