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 466 篇，第 3 / 10 页

101. NeurIPS 2024Diffusion-Reward Adversarial Imitation Learning
102. NeurIPS 2024DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
103. NeurIPS 2024Discovering Creative Behaviors through DUPLEX: Diverse Universal Features for Policy Exploration
104. NeurIPS 2024Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
105. NeurIPS 2024Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation
106. NeurIPS 2024Distributional Reinforcement Learning with Regularized Wasserstein Loss
107. NeurIPS 2024Distributional Successor Features Enable Zero-Shot Policy Optimization
108. NeurIPS 2024Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms
109. NeurIPS 2024Diversity Is Not All You Need: Training A Robust Cooperative Agent Needs Specialist Partners
110. NeurIPS 2024DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors
111. NeurIPS 2024Do LLMs Build World Representations? Probing Through the Lens of State Abstraction
112. NeurIPS 2024Do's and Don'ts: Learning Desirable Skills with Instruction Videos
113. NeurIPS 2024dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
114. NeurIPS 2024Doubly Mild Generalization for Offline Reinforcement Learning
115. NeurIPS 2024Dual Critic Reinforcement Learning under Partial Observability
116. NeurIPS 2024Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
117. NeurIPS 2024Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron
118. NeurIPS 2024DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
119. NeurIPS 2024e-COP : Episodic Constrained Optimization of Policies
120. NeurIPS 2024E-Motion: Future Motion Simulation via Event Sequence Diffusion
121. NeurIPS 2024EASI: Evolutionary Adversarial Simulator Identification for Sim-to-Real Transfer
122. NeurIPS 2024Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
123. NeurIPS 2024Effective Exploration Based on the Structural Information Principles
124. NeurIPS 2024Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes
125. NeurIPS 2024Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
126. NeurIPS 2024Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance
127. NeurIPS 2024Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
128. NeurIPS 2024Efficient Reinforcement Learning by Discovering Neural Pathways
129. NeurIPS 2024Embedding-Aligned Language Models
130. NeurIPS 2024Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity
131. NeurIPS 2024Enhancing Chess Reinforcement Learning with Graph Representation
132. NeurIPS 2024Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
133. NeurIPS 2024Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
134. NeurIPS 2024Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach
135. NeurIPS 2024Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning
136. NeurIPS 2024Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
137. NeurIPS 2024EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes
138. NeurIPS 2024Episodic Future Thinking Mechanism for Multi-agent Reinforcement Learning
139. NeurIPS 2024Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking
140. NeurIPS 2024Exclusively Penalized Q-learning for Offline Reinforcement Learning
141. NeurIPS 2024Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch
142. NeurIPS 2024Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration
143. NeurIPS 2024Exploration by Learning Diverse Skills through Successor State Representations
144. NeurIPS 2024Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
145. NeurIPS 2024Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning
146. NeurIPS 2024FactorSim: Generative Simulation via Factorized Representation
147. NeurIPS 2024Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
148. NeurIPS 2024Federated Ensemble-Directed Offline Reinforcement Learning
149. NeurIPS 2024Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
150. NeurIPS 2024Feint Behaviors and Strategies: Formalization, Implementation and Evaluation

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。