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 1,190 篇，第 2 / 24 页

51. CVPR 2024ReCoRe: Regularized Contrastive Representation Learning of World Model
52. CVPR 2024Regularized Parameter Uncertainty for Improving Generalization in Reinforcement Learning
53. CVPR 2024RepViT: Revisiting Mobile CNN From ViT Perspective
54. CVPR 2024Rich Human Feedback for Text-to-Image Generation
55. CVPR 2024RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation
56. CVPR 2024Robust Self-calibration of Focal Lengths from the Fundamental Matrix
57. CVPR 2024Selective Nonlinearities Removal from Digital Signals
58. CVPR 2024Small Scale Data-Free Knowledge Distillation
59. CVPR 2024SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos
60. CVPR 2024SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World
61. CVPR 2024Super-Resolution Reconstruction from Bayer-Pattern Spike Streams
62. CVPR 2024Training Diffusion Models Towards Diverse Image Generation with Reinforcement Learning
63. CVPR 2024Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
64. CVPR 2024WANDR: Intention-guided Human Motion Generation
65. ICLR 2024$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
66. ICLR 2024$\pi$2vec: Policy Representation with Successor Features
67. ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
68. ICLR 2024A Dynamical View of the Question of Why
69. ICLR 2024A Newborn Embodied Turing Test for Comparing Object Segmentation Across Animals and Machines
70. ICLR 2024A Policy Gradient Method for Confounded POMDPs
71. ICLR 2024Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
72. ICLR 2024Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
73. ICLR 2024Active Retrosynthetic Planning Aware of Route Quality
74. ICLR 2024Adaptive Rational Activations to Boost Deep Reinforcement Learning
75. ICLR 2024Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation
76. ICLR 2024Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning
77. ICLR 2024Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
78. ICLR 2024Addressing Signal Delay in Deep Reinforcement Learning
79. ICLR 2024Adversarial Imitation Learning via Boosting
80. ICLR 2024AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
81. ICLR 2024AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents
82. ICLR 2024Amortized Network Intervention to Steer the Excitatory Point Processes
83. ICLR 2024Amortizing intractable inference in large language models
84. ICLR 2024ASID: Active Exploration for System Identification in Robotic Manipulation
85. ICLR 2024Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement Learning
86. ICLR 2024Augmented Bayesian Policy Search
87. ICLR 2024Beam Enumeration: Probabilistic Explainability For Sample Efficient Self-conditioned Molecular Design
88. ICLR 2024Behaviour Distillation
89. ICLR 2024Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations
90. ICLR 2024Better Neural PDE Solvers Through Data-Free Mesh Movers
91. ICLR 2024Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment
92. ICLR 2024Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
93. ICLR 2024Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods
94. ICLR 2024Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
95. ICLR 2024Blending Imitation and Reinforcement Learning for Robust Policy Improvement
96. ICLR 2024Bridging State and History Representations: Understanding Self-Predictive RL
97. ICLR 2024Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
98. ICLR 2024Cascading Reinforcement Learning
99. ICLR 2024Causally Aligned Curriculum Learning
100. ICLR 2024Chain of Hindsight aligns Language Models with Feedback

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。