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 356 篇，第 6 / 8 页

251. ICML 2024Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation
252. ICML 2024Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback
253. ICML 2024Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
254. ICML 2024Q-value Regularized Transformer for Offline Reinforcement Learning
255. ICML 2024QORA: Zero-Shot Transfer via Interpretable Object-Relational Model Learning
256. ICML 2024Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization
257. ICML 2024Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics
258. ICML 2024Quality-Diversity with Limited Resources
259. ICML 2024Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design
260. ICML 2024Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency
261. ICML 2024Random Latent Exploration for Deep Reinforcement Learning
262. ICML 2024Rate-Optimal Policy Optimization for Linear Markov Decision Processes
263. ICML 2024Recovering Labels from Local Updates in Federated Learning
264. ICML 2024ReDiffuser: Reliable Decision-Making Using a Diffuser with Confidence Estimation
265. ICML 2024Refining Minimax Regret for Unsupervised Environment Design
266. ICML 2024Reflective Policy Optimization
267. ICML 2024Reinforcement Learning and Regret Bounds for Admission Control
268. ICML 2024Reinforcement Learning from Reachability Specifications: PAC Guarantees with Expected Conditional Distance
269. ICML 2024Reinforcement Learning within Tree Search for Fast Macro Placement
270. ICML 2024Reinformer: Max-Return Sequence Modeling for Offline RL
271. ICML 2024ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
272. ICML 2024ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
273. ICML 2024Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making
274. ICML 2024Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation
275. ICML 2024Rethinking Decision Transformer via Hierarchical Reinforcement Learning
276. ICML 2024Rethinking Transformers in Solving POMDPs
277. ICML 2024Revisiting Inexact Fixed-Point Iterations for Min-Max Problems: Stochasticity and Structured Nonconvexity
278. ICML 2024Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
279. ICML 2024Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
280. ICML 2024Reward Shaping for Reinforcement Learning with An Assistant Reward Agent
281. ICML 2024Reward-Free Kernel-Based Reinforcement Learning
282. ICML 2024Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
283. ICML 2024RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
284. ICML 2024Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
285. ICML 2024RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences
286. ICML 2024Risk-Sensitive Policy Optimization via Predictive CVaR Policy Gradient
287. ICML 2024Risk-Sensitive Reward-Free Reinforcement Learning with CVaR
288. ICML 2024RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning
289. ICML 2024RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback
290. ICML 2024RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
291. ICML 2024RLVF: Learning from Verbal Feedback without Overgeneralization
292. ICML 2024RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
293. ICML 2024Robust Inverse Constrained Reinforcement Learning under Model Misspecification
294. ICML 2024Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space
295. ICML 2024Run-Time Task Composition with Safety Semantics
296. ICML 2024RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning
297. ICML 2024Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
298. ICML 2024Sample Average Approximation for Conditional Stochastic Optimization with Dependent Data
299. ICML 2024Sample-Efficient Multiagent Reinforcement Learning with Reset Replay
300. ICML 2024Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty

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。