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 484 篇，第 1 / 10 页

1. NeurIPS 2023“Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization
2. NeurIPS 2023$\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
3. NeurIPS 2023A Definition of Continual Reinforcement Learning
4. NeurIPS 2023A Long $N$-step Surrogate Stage Reward for Deep Reinforcement Learning
5. NeurIPS 2023A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence
6. NeurIPS 2023A Partially-Supervised Reinforcement Learning Framework for Visual Active Search
7. NeurIPS 2023A Reduction-based Framework for Sequential Decision Making with Delayed Feedback
8. NeurIPS 2023A Robust and Opponent-Aware League Training Method for StarCraft II
9. NeurIPS 2023A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories
10. NeurIPS 2023A State Representation for Diminishing Rewards
11. NeurIPS 2023A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes
12. NeurIPS 2023A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning
13. NeurIPS 2023A Trichotomy for Transductive Online Learning
14. NeurIPS 2023A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process
15. NeurIPS 2023Accelerating Exploration with Unlabeled Prior Data
16. NeurIPS 2023Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction
17. NeurIPS 2023Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration
18. NeurIPS 2023Accelerating Value Iteration with Anchoring
19. NeurIPS 2023Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples
20. NeurIPS 2023Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
21. NeurIPS 2023Active Observing in Continuous-time Control
22. NeurIPS 2023Active Vision Reinforcement Learning under Limited Visual Observability
23. NeurIPS 2023Adaptive Online Replanning with Diffusion Models
24. NeurIPS 2023Adjustable Robust Reinforcement Learning for Online 3D Bin Packing
25. NeurIPS 2023Adversarial Counterfactual Environment Model Learning
26. NeurIPS 2023Adversarial Model for Offline Reinforcement Learning
27. NeurIPS 2023AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation
28. NeurIPS 2023Aligning Language Models with Human Preferences via a Bayesian Approach
29. NeurIPS 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
30. NeurIPS 2023An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition
31. NeurIPS 2023An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient
32. NeurIPS 2023An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits
33. NeurIPS 2023Anytime-Competitive Reinforcement Learning with Policy Prior
34. NeurIPS 2023Arbitrarily Scalable Environment Generators via Neural Cellular Automata
35. NeurIPS 2023Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning
36. NeurIPS 2023AVIDa-hIL6: A Large-Scale VHH Dataset Produced from an Immunized Alpaca for Predicting Antigen-Antibody Interactions
37. NeurIPS 2023Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space
38. NeurIPS 2023Bayesian Learning via Q-Exponential Process
39. NeurIPS 2023Bayesian Risk-Averse Q-Learning with Streaming Observations
40. NeurIPS 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
41. NeurIPS 2023Behavior Alignment via Reward Function Optimization
42. NeurIPS 2023Belief Projection-Based Reinforcement Learning for Environments with Delayed Feedback
43. NeurIPS 2023Beyond Average Return in Markov Decision Processes
44. NeurIPS 2023Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence
45. NeurIPS 2023Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets
46. NeurIPS 2023Bi-Level Offline Policy Optimization with Limited Exploration
47. NeurIPS 2023Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm
48. NeurIPS 2023BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning
49. NeurIPS 2023Blockwise Parallel Transformers for Large Context Models
50. NeurIPS 2023Boosting Verification of Deep Reinforcement Learning via Piece-Wise Linear Decision Neural Networks

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。