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 2,494 篇，第 43 / 50 页

2101. NeurIPS 2023Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning
2102. NeurIPS 2023Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
2103. NeurIPS 2023CQM: Curriculum Reinforcement Learning with a Quantized World Model
2104. NeurIPS 2023Creating Multi-Level Skill Hierarchies in Reinforcement Learning
2105. NeurIPS 2023Cross-Domain Policy Adaptation via Value-Guided Data Filtering
2106. NeurIPS 2023Cross-Episodic Curriculum for Transformer Agents
2107. NeurIPS 2023CS-Isolate: Extracting Hard Confident Examples by Content and Style Isolation
2108. NeurIPS 2023Data Quality in Imitation Learning
2109. NeurIPS 2023Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances
2110. NeurIPS 2023De novo Drug Design using Reinforcement Learning with Multiple GPT Agents
2111. NeurIPS 2023Debiased and Denoised Entity Recognition from Distant Supervision
2112. NeurIPS 2023Debiasing Conditional Stochastic Optimization
2113. NeurIPS 2023Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models
2114. NeurIPS 2023Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees
2115. NeurIPS 2023Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning
2116. NeurIPS 2023Deep Reinforcement Learning with Plasticity Injection
2117. NeurIPS 2023DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization
2118. NeurIPS 2023Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization
2119. NeurIPS 2023DIFFER:Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning
2120. NeurIPS 2023Diffused Task-Agnostic Milestone Planner
2121. NeurIPS 2023Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
2122. NeurIPS 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Model
2123. NeurIPS 2023Direct Preference-based Policy Optimization without Reward Modeling
2124. NeurIPS 2023Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms
2125. NeurIPS 2023Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design
2126. NeurIPS 2023Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning
2127. NeurIPS 2023Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning
2128. NeurIPS 2023Distributional Pareto-Optimal Multi-Objective Reinforcement Learning
2129. NeurIPS 2023Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning
2130. NeurIPS 2023Diversify \& Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement
2131. NeurIPS 2023Domain Adaptive Imitation Learning with Visual Observation
2132. NeurIPS 2023Double Gumbel Q-Learning
2133. NeurIPS 2023Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage
2134. NeurIPS 2023Doubly Robust Augmented Transfer for Meta-Reinforcement Learning
2135. NeurIPS 2023DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
2136. NeurIPS 2023Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative MARL
2137. NeurIPS 2023DynaDojo: An Extensible Benchmarking Platform for Scalable Dynamical System Identification
2138. NeurIPS 2023Dynamic Regret of Adversarial Linear Mixture MDPs
2139. NeurIPS 2023Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies
2140. NeurIPS 2023Easy Learning from Label Proportions
2141. NeurIPS 2023Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning
2142. NeurIPS 2023Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning
2143. NeurIPS 2023Efficient Diffusion Policies For Offline Reinforcement Learning
2144. NeurIPS 2023Efficient Exploration in Continuous-time Model-based Reinforcement Learning
2145. NeurIPS 2023Efficient Hyper-parameter Optimization with Cubic Regularization
2146. NeurIPS 2023Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization
2147. NeurIPS 2023Efficient Model-Free Exploration in Low-Rank MDPs
2148. NeurIPS 2023Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents
2149. NeurIPS 2023Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric
2150. NeurIPS 2023Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations

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。