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 297 篇，第 3 / 6 页

101. ICML 2023Hindsight Learning for MDPs with Exogenous Inputs
102. ICML 2023Homomorphism AutoEncoder --- Learning Group Structured Representations from Observed Transitions
103. ICML 2023Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes
104. ICML 2023Horizon-free Learning for Markov Decision Processes and Games: Stochastically Bounded Rewards and Improved Bounds
105. ICML 2023Human-Timescale Adaptation in an Open-Ended Task Space
106. ICML 2023Hyperparameters in Reinforcement Learning and How To Tune Them
107. ICML 2023Identifiability and Generalizability in Constrained Inverse Reinforcement Learning
108. ICML 2023Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation
109. ICML 2023Improving Bi-level Optimization Based Methods with Inspiration from Humans' Classroom Study Techniques
110. ICML 2023Individually Fair Learning with One-Sided Feedback
111. ICML 2023Information-Theoretic State Space Model for Multi-View Reinforcement Learning
112. ICML 2023Interactive Object Placement with Reinforcement Learning
113. ICML 2023Internally Rewarded Reinforcement Learning
114. ICML 2023Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
115. ICML 2023Inverse Reinforcement Learning without Reinforcement Learning
116. ICML 2023Investigating the Role of Model-Based Learning in Exploration and Transfer
117. ICML 2023Jump-Start Reinforcement Learning
118. ICML 2023Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning
119. ICML 2023Language Instructed Reinforcement Learning for Human-AI Coordination
120. ICML 2023Lazy Agents: A New Perspective on Solving Sparse Reward Problem in Multi-agent Reinforcement Learning
121. ICML 2023Learning Belief Representations for Partially Observable Deep RL
122. ICML 2023Learning Compiler Pass Orders using Coreset and Normalized Value Prediction
123. ICML 2023Learning Control-Oriented Dynamical Structure from Data
124. ICML 2023Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees
125. ICML 2023Learning GFlowNets From Partial Episodes For Improved Convergence And Stability
126. ICML 2023Learning in POMDPs is Sample-Efficient with Hindsight Observability
127. ICML 2023Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics
128. ICML 2023Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation
129. ICML 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping
130. ICML 2023Learning Temporally AbstractWorld Models without Online Experimentation
131. ICML 2023Learning the Dynamics of Sparsely Observed Interacting Systems
132. ICML 2023Learning to Design Analog Circuits to Meet Threshold Specifications
133. ICML 2023Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
134. ICML 2023Learning to Maximize Mutual Information for Dynamic Feature Selection
135. ICML 2023Learning to Optimize Differentiable Games
136. ICML 2023Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator
137. ICML 2023Learning useful representations for shifting tasks and distributions
138. ICML 2023LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework
139. ICML 2023Leveraging Offline Data in Online Reinforcement Learning
140. ICML 2023LinSATNet: The Positive Linear Satisfiability Neural Networks
141. ICML 2023LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control
142. ICML 2023LIV: Language-Image Representations and Rewards for Robotic Control
143. ICML 2023Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy
144. ICML 2023Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning
145. ICML 2023Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling
146. ICML 2023Lower Bounds for Learning in Revealing POMDPs
147. ICML 2023MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations
148. ICML 2023MANSA: Learning Fast and Slow in Multi-Agent Systems
149. ICML 2023Masked Trajectory Models for Prediction, Representation, and Control
150. ICML 2023Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels

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。