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 233 篇，第 4 / 5 页

151. ICLR 2023Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics
152. ICLR 2023Order Matters: Agent-by-agent Policy Optimization
153. ICLR 2023Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation
154. ICLR 2023PAC Reinforcement Learning for Predictive State Representations
155. ICLR 2023Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms
156. ICLR 2023PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm
157. ICLR 2023Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs
158. ICLR 2023Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
159. ICLR 2023Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning
160. ICLR 2023Planning Goals for Exploration
161. ICLR 2023Planning with Sequence Models through Iterative Energy Minimization
162. ICLR 2023Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
163. ICLR 2023Policy-Based Self-Competition for Planning Problems
164. ICLR 2023POPGym: Benchmarking Partially Observable Reinforcement Learning
165. ICLR 2023Population-size-Aware Policy Optimization for Mean-Field Games
166. ICLR 2023Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
167. ICLR 2023Preference Transformer: Modeling Human Preferences using Transformers for RL
168. ICLR 2023Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning
169. ICLR 2023Proactive Multi-Camera Collaboration for 3D Human Pose Estimation
170. ICLR 2023Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks
171. ICLR 2023Provably Efficient Lifelong Reinforcement Learning with Linear Representation
172. ICLR 2023Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path
173. ICLR 2023Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots
174. ICLR 2023Quality-Similar Diversity via Population Based Reinforcement Learning
175. ICLR 2023Quasi-optimal Reinforcement Learning with Continuous Actions
176. ICLR 2023ReAct: Synergizing Reasoning and Acting in Language Models
177. ICLR 2023Recursive Time Series Data Augmentation
178. ICLR 2023Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences
179. ICLR 2023Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay
180. ICLR 2023Represent to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency
181. ICLR 2023Representation Learning for Low-rank General-sum Markov Games
182. ICLR 2023ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor
183. ICLR 2023Revisiting Intrinsic Reward for Exploration in Procedurally Generated Environments
184. ICLR 2023Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching
185. ICLR 2023Reward Design with Language Models
186. ICLR 2023Risk-Aware Reinforcement Learning with Coherent Risk Measures and Non-linear Function Approximation
187. ICLR 2023RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
188. ICLR 2023ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs
189. ICLR 2023RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning
190. ICLR 2023Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-Free RL
191. ICLR 2023Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation
192. ICLR 2023Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks
193. ICLR 2023Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier
194. ICLR 2023Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing
195. ICLR 2023Scaling Laws for a Multi-Agent Reinforcement Learning Model
196. ICLR 2023Scaling Pareto-Efficient Decision Making via Offline Multi-Objective RL
197. ICLR 2023Simple Emergent Action Representations from Multi-Task Policy Training
198. ICLR 2023Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective
199. ICLR 2023SMART: Self-supervised Multi-task pretrAining with contRol Transformers
200. ICLR 2023Solving Continuous Control via Q-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。