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 356 篇，第 4 / 8 页

151. ICML 2024Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
152. ICML 2024Learning a Diffusion Model Policy from Rewards via Q-Score Matching
153. ICML 2024Learning Causal Dynamics Models in Object-Oriented Environments
154. ICML 2024Learning Constraints from Offline Demonstrations via Superior Distribution Correction Estimation
155. ICML 2024Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning
156. ICML 2024Learning Decision Policies with Instrumental Variables through Double Machine Learning
157. ICML 2024Learning Decision Trees and Forests with Algorithmic Recourse
158. ICML 2024Learning from Streaming Data when Users Choose
159. ICML 2024Learning Latent Dynamic Robust Representations for World Models
160. ICML 2024Learning Optimal Deterministic Policies with Stochastic Policy Gradients
161. ICML 2024Learning Surrogates for Offline Black-Box Optimization via Gradient Matching
162. ICML 2024Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
163. ICML 2024Learning the Target Network in Function Space
164. ICML 2024Learning to Play Atari in a World of Tokens
165. ICML 2024Learning to Reach Goals via Diffusion
166. ICML 2024Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces
167. ICML 2024Learning with 3D rotations, a hitchhiker's guide to SO(3)
168. ICML 2024Limited Preference Aided Imitation Learning from Imperfect Demonstrations
169. ICML 2024Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
170. ICML 2024Linguistic Calibration of Long-Form Generations
171. ICML 2024Listwise Reward Estimation for Offline Preference-based Reinforcement Learning
172. ICML 2024LLM-Empowered State Representation for Reinforcement Learning
173. ICML 2024Logistic Variational Bayes Revisited
174. ICML 2024Major-Minor Mean Field Multi-Agent Reinforcement Learning
175. ICML 2024MaxMin-RLHF: Alignment with Diverse Human Preferences
176. ICML 2024Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy Learning
177. ICML 2024Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective
178. ICML 2024Meta-Reinforcement Learning Robust to Distributional Shift Via Performing Lifelong In-Context Learning
179. ICML 2024Mind the Boundary: Coreset Selection via Reconstructing the Decision Boundary
180. ICML 2024Mixtures of Experts Unlock Parameter Scaling for Deep RL
181. ICML 2024MLI Formula: A Nearly Scale-Invariant Solution with Noise Perturbation
182. ICML 2024Model-based Reinforcement Learning for Confounded POMDPs
183. ICML 2024Model-based Reinforcement Learning for Parameterized Action Spaces
184. ICML 2024Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL
185. ICML 2024Model-Free Robust $\phi$-Divergence Reinforcement Learning Using Both Offline and Online Data
186. ICML 2024Mollification Effects of Policy Gradient Methods
187. ICML 2024Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments
188. ICML 2024More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning
189. ICML 2024Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy
190. ICML 2024Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder Stationing
191. ICML 2024Multi-View Clustering by Inter-cluster Connectivity Guided Reward
192. ICML 2024MusicRL: Aligning Music Generation to Human Preferences
193. ICML 2024Nash Learning from Human Feedback
194. ICML 2024Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback
195. ICML 2024Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints
196. ICML 2024Neural-Kernel Conditional Mean Embeddings
197. ICML 2024No-Regret Reinforcement Learning in Smooth MDPs
198. ICML 2024Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation
199. ICML 2024Nonlinear Filtering with Brenier Optimal Transport Maps
200. ICML 2024ODIN: Disentangled Reward Mitigates Hacking in RLHF

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。