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 6,885 篇，第 103 / 138 页

5101. ICML 2024Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees
5102. ICML 2024Fundamental Limitations of Alignment in Large Language Models
5103. ICML 2024FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning
5104. ICML 2024Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction
5105. ICML 2024GFlowNet Training by Policy Gradients
5106. ICML 2024Global Reinforcement Learning : Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods
5107. ICML 2024Hard Tasks First: Multi-Task Reinforcement Learning Through Task Scheduling
5108. ICML 2024HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
5109. ICML 2024HarmonyDream: Task Harmonization Inside World Models
5110. ICML 2024HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention Network
5111. ICML 2024HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming
5112. ICML 2024Hieros: Hierarchical Imagination on Structured State Space Sequence World Models
5113. ICML 2024How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
5114. ICML 2024How Does Goal Relabeling Improve Sample Efficiency?
5115. ICML 2024How to Explore with Belief: State Entropy Maximization in POMDPs
5116. ICML 2024How to Leverage Diverse Demonstrations in Offline Imitation Learning
5117. ICML 2024Human Alignment of Large Language Models through Online Preference Optimisation
5118. ICML 2024Hybrid Inverse Reinforcement Learning
5119. ICML 2024Hybrid Reinforcement Learning from Offline Observation Alone
5120. ICML 2024Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States
5121. ICML 2024Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements
5122. ICML 2024Improving Generalization in Offline Reinforcement Learning via Adversarial Data Splitting
5123. ICML 2024Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
5124. ICML 2024Improving Token-Based World Models with Parallel Observation Prediction
5125. ICML 2024In value-based deep reinforcement learning, a pruned network is a good network
5126. ICML 2024In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
5127. ICML 2024In-Context Learning Agents Are Asymmetric Belief Updaters
5128. ICML 2024In-Context Reinforcement Learning for Variable Action Spaces
5129. ICML 2024Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning
5130. ICML 2024Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting
5131. ICML 2024Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments
5132. ICML 2024Information-Directed Pessimism for Offline Reinforcement Learning
5133. ICML 2024Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
5134. ICML 2024INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer
5135. ICML 2024Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
5136. ICML 2024Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective
5137. ICML 2024Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
5138. ICML 2024Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint
5139. ICML 2024Iterative Regularized Policy Optimization with Imperfect Demonstrations
5140. ICML 2024Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations
5141. ICML 2024LAGMA: LAtent Goal-guided Multi-Agent Reinforcement Learning
5142. ICML 2024Langevin Policy for Safe Reinforcement Learning
5143. ICML 2024Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game
5144. ICML 2024Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
5145. ICML 2024Learning a Diffusion Model Policy from Rewards via Q-Score Matching
5146. ICML 2024Learning Causal Dynamics Models in Object-Oriented Environments
5147. ICML 2024Learning Constraints from Offline Demonstrations via Superior Distribution Correction Estimation
5148. ICML 2024Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning
5149. ICML 2024Learning Decision Policies with Instrumental Variables through Double Machine Learning
5150. ICML 2024Learning Decision Trees and Forests with Algorithmic Recourse

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。