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 1,070 篇，第 3 / 22 页

101. ICLR 2023Decision Transformer under Random Frame Dropping
102. ICLR 2023Deep Generative Symbolic Regression
103. ICLR 2023Deep Reinforcement Learning for Cost-Effective Medical Diagnosis
104. ICLR 2023DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
105. ICLR 2023DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics
106. ICLR 2023Dichotomy of Control: Separating What You Can Control from What You Cannot
107. ICLR 2023DiffMimic: Efficient Motion Mimicking with Differentiable Physics
108. ICLR 2023Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
109. ICLR 2023Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning
110. ICLR 2023Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data
111. ICLR 2023Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality
112. ICLR 2023Distributional Meta-Gradient Reinforcement Learning
113. ICLR 2023Does Zero-Shot Reinforcement Learning Exist?
114. ICLR 2023Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
115. ICLR 2023Efficient Deep Reinforcement Learning Requires Regulating Overfitting
116. ICLR 2023Efficient Offline Policy Optimization with a Learned Model
117. ICLR 2023Efficient Planning in a Compact Latent Action Space
118. ICLR 2023Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
119. ICLR 2023Emergence of Maps in the Memories of Blind Navigation Agents
120. ICLR 2023ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation
121. ICLR 2023ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret
122. ICLR 2023EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model
123. ICLR 2023Evaluating Long-Term Memory in 3D Mazes
124. ICLR 2023Evolving Populations of Diverse RL Agents with MAP-Elites
125. ICLR 2023Explaining RL Decisions with Trajectories
126. ICLR 2023Extreme Q-Learning: MaxEnt RL without Entropy
127. ICLR 2023Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems
128. ICLR 2023Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
129. ICLR 2023FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
130. ICLR 2023From $t$-SNE to UMAP with contrastive learning
131. ICLR 2023From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data
132. ICLR 2023Generalize Learned Heuristics to Solve Large-scale Vehicle Routing Problems in Real-time
133. ICLR 2023Generating Diverse Cooperative Agents by Learning Incompatible Policies
134. ICLR 2023Generative Augmented Flow Networks
135. ICLR 2023GFlowNets and variational inference
136. ICLR 2023GoBigger: A Scalable Platform for Cooperative-Competitive Multi-Agent Interactive Simulation
137. ICLR 2023Graph-based Deterministic Policy Gradient for Repetitive Combinatorial Optimization Problems
138. ICLR 2023Gray-Box Gaussian Processes for Automated Reinforcement Learning
139. ICLR 2023Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement
140. ICLR 2023Guarded Policy Optimization with Imperfect Online Demonstrations
141. ICLR 2023Guiding Safe Exploration with Weakest Preconditions
142. ICLR 2023Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting
143. ICLR 2023HiT-MDP: Learning the SMDP option framework on MDPs with Hidden Temporal Embeddings
144. ICLR 2023Human-level Atari 200x faster
145. ICLR 2023Hybrid RL: Using both offline and online data can make RL efficient
146. ICLR 2023Hyper-Decision Transformer for Efficient Online Policy Adaptation
147. ICLR 2023Hyperbolic Deep Reinforcement Learning
148. ICLR 2023Imitating Graph-Based Planning with Goal-Conditioned Policies
149. ICLR 2023Impossibly Good Experts and How to Follow Them
150. ICLR 2023Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs

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。