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 297 篇，第 2 / 6 页

51. ICML 2023Curious Replay for Model-based Adaptation
52. ICML 2023Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity
53. ICML 2023Deep Laplacian-based Options for Temporally-Extended Exploration
54. ICML 2023Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback
55. ICML 2023Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum
56. ICML 2023Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions
57. ICML 2023Differentiable and Transportable Structure Learning
58. ICML 2023Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards
59. ICML 2023Discovering Object-Centric Generalized Value Functions From Pixels
60. ICML 2023Distance Weighted Supervised Learning for Offline Interaction Data
61. ICML 2023Distributional Offline Policy Evaluation with Predictive Error Guarantees
62. ICML 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling
63. ICML 2023Does Sparsity Help in Learning Misspecified Linear Bandits?
64. ICML 2023Dynamical Linear Bandits
65. ICML 2023ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines
66. ICML 2023Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization
67. ICML 2023Efficient Online Reinforcement Learning with Offline Data
68. ICML 2023Emergence of Adaptive Circadian Rhythms in Deep Reinforcement Learning
69. ICML 2023Emergence of Sparse Representations from Noise
70. ICML 2023Emergent Agentic Transformer from Chain of Hindsight Experience
71. ICML 2023Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments
72. ICML 2023Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning
73. ICML 2023Estimating Heterogeneous Treatment Effects: Mutual Information Bounds and Learning Algorithms
74. ICML 2023Estimation Beyond Data Reweighting: Kernel Method of Moments
75. ICML 2023Explainable Data-Driven Optimization: From Context to Decision and Back Again
76. ICML 2023Explaining Reinforcement Learning with Shapley Values
77. ICML 2023Fair and Robust Estimation of Heterogeneous Treatment Effects for Policy Learning
78. ICML 2023Fair Densities via Boosting the Sufficient Statistics of Exponential Families
79. ICML 2023Fair yet Asymptotically Equal Collaborative Learning
80. ICML 2023Faith-Shap: The Faithful Shapley Interaction Index
81. ICML 2023Fast Rates for Maximum Entropy Exploration
82. ICML 2023Federated Online and Bandit Convex Optimization
83. ICML 2023FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems
84. ICML 2023Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning
85. ICML 2023For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal
86. ICML 2023FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning
87. ICML 2023From Hypergraph Energy Functions to Hypergraph Neural Networks
88. ICML 2023From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning
89. ICML 2023Fundamental Tradeoffs in Learning with Prior Information
90. ICML 2023Future-conditioned Unsupervised Pretraining for Decision Transformer
91. ICML 2023GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models
92. ICML 2023Go Beyond Imagination: Maximizing Episodic Reachability with World Models
93. ICML 2023Graph Reinforcement Learning for Network Control via Bi-Level Optimization
94. ICML 2023Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
95. ICML 2023Guiding Pretraining in Reinforcement Learning with Large Language Models
96. ICML 2023Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games
97. ICML 2023Hierarchical Diffusion for Offline Decision Making
98. ICML 2023Hierarchical Imitation Learning with Vector Quantized Models
99. ICML 2023Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs
100. ICML 2023Hierarchies of Reward Machines

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。