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 2 / 10 页

51. NeurIPS 2023Boosting with Tempered Exponential Measures
52. NeurIPS 2023Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences
53. NeurIPS 2023BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization
54. NeurIPS 2023Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback
55. NeurIPS 2023Bridging RL Theory and Practice with the Effective Horizon
56. NeurIPS 2023Budgeting Counterfactual for Offline RL
57. NeurIPS 2023Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
58. NeurIPS 2023CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room Scenes
59. NeurIPS 2023Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?
60. NeurIPS 2023CEIL: Generalized Contextual Imitation Learning
61. NeurIPS 2023Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception
62. NeurIPS 2023Chatting Makes Perfect: Chat-based Image Retrieval
63. NeurIPS 2023Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity
64. NeurIPS 2023Classical Simulation of Quantum Circuits: Parallel Environments and Benchmark
65. NeurIPS 2023Closing the Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits
66. NeurIPS 2023Coherent Soft Imitation Learning
67. NeurIPS 2023Combinatorial Optimization with Policy Adaptation using Latent Space Search
68. NeurIPS 2023Combining Behaviors with the Successor Features Keyboard
69. NeurIPS 2023Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems
70. NeurIPS 2023Complexity of Derivative-Free Policy Optimization for Structured $\mathcal{H}_\infty$ Control
71. NeurIPS 2023Compositional Generalization from First Principles
72. NeurIPS 2023Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees
73. NeurIPS 2023Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games
74. NeurIPS 2023Conditional Mutual Information for Disentangled Representations in Reinforcement Learning
75. NeurIPS 2023Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model
76. NeurIPS 2023Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems
77. NeurIPS 2023Conservative Offline Policy Adaptation in Multi-Agent Games
78. NeurIPS 2023Conservative State Value Estimation for Offline Reinforcement Learning
79. NeurIPS 2023Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards
80. NeurIPS 2023Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning
81. NeurIPS 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
82. NeurIPS 2023Context Shift Reduction for Offline Meta-Reinforcement Learning
83. NeurIPS 2023Contextual Bandits and Imitation Learning with Preference-Based Active Queries
84. NeurIPS 2023Continual Learning for Instruction Following from Realtime Feedback
85. NeurIPS 2023Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning
86. NeurIPS 2023Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
87. NeurIPS 2023Convergence of Actor-Critic with Multi-Layer Neural Networks
88. NeurIPS 2023COOM: A Game Benchmark for Continual Reinforcement Learning
89. NeurIPS 2023CORL: Research-oriented Deep Offline Reinforcement Learning Library
90. NeurIPS 2023Corruption-Robust Offline Reinforcement Learning with General Function Approximation
91. NeurIPS 2023Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning
92. NeurIPS 2023Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
93. NeurIPS 2023CQM: Curriculum Reinforcement Learning with a Quantized World Model
94. NeurIPS 2023Creating Multi-Level Skill Hierarchies in Reinforcement Learning
95. NeurIPS 2023Cross-Domain Policy Adaptation via Value-Guided Data Filtering
96. NeurIPS 2023Cross-Episodic Curriculum for Transformer Agents
97. NeurIPS 2023CS-Isolate: Extracting Hard Confident Examples by Content and Style Isolation
98. NeurIPS 2023Data Quality in Imitation Learning
99. NeurIPS 2023Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances
100. NeurIPS 2023De novo Drug Design using Reinforcement Learning with Multiple GPT Agents

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。