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 105 / 138 页

5201. ICML 2024OMPO: A Unified Framework for RL under Policy and Dynamics Shifts
5202. ICML 2024On the Second-Order Convergence of Biased Policy Gradient Algorithms
5203. ICML 2024On The Statistical Complexity of Offline Decision-Making
5204. ICML 2024On the Unexpected Effectiveness of Reinforcement Learning for Sequential Recommendation
5205. ICML 2024On Which Nodes Does GCN Fail? Enhancing GCN From the Node Perspective
5206. ICML 2024Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement Learning
5207. ICML 2024Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization
5208. ICML 2024OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos
5209. ICML 2024Overcoming the Optimizer's Curse: Obtaining Realistic Prescriptions from Neural Networks
5210. ICML 2024Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
5211. ICML 2024Parameter Estimation in DAGs from Incomplete Data via Optimal Transport
5212. ICML 2024Pausing Policy Learning in Non-stationary Reinforcement Learning
5213. ICML 2024PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
5214. ICML 2024Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning
5215. ICML 2024Pi-DUAL: Using privileged information to distinguish clean from noisy labels
5216. ICML 2024PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning
5217. ICML 2024PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling
5218. ICML 2024PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer
5219. ICML 2024Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners
5220. ICML 2024Policy Evaluation for Variance in Average Reward Reinforcement Learning
5221. ICML 2024Policy Learning for Balancing Short-Term and Long-Term Rewards
5222. ICML 2024Policy-conditioned Environment Models are More Generalizable
5223. ICML 2024Position: Amazing Things Come From Having Many Good Models
5224. ICML 2024Position: Automatic Environment Shaping is the Next Frontier in RL
5225. ICML 2024Position: Benchmarking is Limited in Reinforcement Learning Research
5226. ICML 2024Position: Insights from Survey Methodology can Improve Training Data
5227. ICML 2024Position: Leverage Foundational Models for Black-Box Optimization
5228. ICML 2024Position: Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination
5229. ICML 2024Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback
5230. ICML 2024Position: Social Environment Design Should be Further Developed for AI-based Policy-Making
5231. ICML 2024Position: Video as the New Language for Real-World Decision Making
5232. ICML 2024Predictive Performance Comparison of Decision Policies Under Confounding
5233. ICML 2024Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
5234. ICML 2024Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF
5235. ICML 2024Privacy-Preserving Instructions for Aligning Large Language Models
5236. ICML 2024Probabilistic Constrained Reinforcement Learning with Formal Interpretability
5237. ICML 2024Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
5238. ICML 2024Probabilistic Subgoal Representations for Hierarchical Reinforcement Learning
5239. ICML 2024Profile Reconstruction from Private Sketches
5240. ICML 2024Prompt-based Visual Alignment for Zero-shot Policy Transfer
5241. ICML 2024Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning
5242. ICML 2024Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation
5243. ICML 2024Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret
5244. ICML 2024Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation
5245. ICML 2024Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback
5246. ICML 2024Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
5247. ICML 2024Q-value Regularized Transformer for Offline Reinforcement Learning
5248. ICML 2024QORA: Zero-Shot Transfer via Interpretable Object-Relational Model Learning
5249. ICML 2024Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization
5250. ICML 2024Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics

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。