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 1,070 篇，第 10 / 22 页

451. ICML 2023Multi-Environment Pretraining Enables Transfer to Action Limited Datasets
452. ICML 2023Multi-task Hierarchical Adversarial Inverse Reinforcement Learning
453. ICML 2023Multi-Task Off-Policy Learning from Bandit Feedback
454. ICML 2023Multi-User Reinforcement Learning with Low Rank Rewards
455. ICML 2023Multiply Robust Off-policy Evaluation and Learning under Truncation by Death
456. ICML 2023N$\text{A}^\text{2}$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning
457. ICML 2023Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR
458. ICML 2023Near-Optimal $\Phi$-Regret Learning in Extensive-Form Games
459. ICML 2023Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints
460. ICML 2023Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes
461. ICML 2023Nested Elimination: A Simple Algorithm for Best-Item Identification From Choice-Based Feedback
462. ICML 2023Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data
463. ICML 2023Non-stationary Reinforcement Learning under General Function Approximation
464. ICML 2023Off-Policy Average Reward Actor-Critic with Deterministic Policy Search
465. ICML 2023Offline Learning in Markov Games with General Function Approximation
466. ICML 2023Offline Meta Reinforcement Learning with In-Distribution Online Adaptation
467. ICML 2023Offline Reinforcement Learning with Closed-Form Policy Improvement Operators
468. ICML 2023On Penalty-based Bilevel Gradient Descent Method
469. ICML 2023On the Convergence of SARSA with Linear Function Approximation
470. ICML 2023On the Effectiveness of Offline RL for Dialogue Response Generation
471. ICML 2023On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures
472. ICML 2023On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning
473. ICML 2023On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness
474. ICML 2023One-sided Matrix Completion from Two Observations Per Row
475. ICML 2023Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
476. ICML 2023Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
477. ICML 2023Optimizing DDPM Sampling with Shortcut Fine-Tuning
478. ICML 2023Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning
479. ICML 2023PAC-Bayesian Offline Contextual Bandits With Guarantees
480. ICML 2023Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation
481. ICML 2023Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing
482. ICML 2023Performative Reinforcement Learning
483. ICML 2023PFNs4BO: In-Context Learning for Bayesian Optimization
484. ICML 2023Policy Contrastive Imitation Learning
485. ICML 2023Policy Evaluation and Temporal-Difference Learning in Continuous Time and Space: A Martingale Approach
486. ICML 2023Policy Gradient in Robust MDPs with Global Convergence Guarantee
487. ICML 2023Policy Regularization with Dataset Constraint for Offline Reinforcement Learning
488. ICML 2023Posterior Sampling for Deep Reinforcement Learning
489. ICML 2023PPG Reloaded: An Empirical Study on What Matters in Phasic Policy Gradient
490. ICML 2023Predictable MDP Abstraction for Unsupervised Model-Based RL
491. ICML 2023Predicting Rare Events by Shrinking Towards Proportional Odds
492. ICML 2023Principled Offline RL in the Presence of Rich Exogenous Information
493. ICML 2023Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons
494. ICML 2023Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning
495. ICML 2023Provable Benefit of Mixup for Finding Optimal Decision Boundaries
496. ICML 2023Provable Reset-free Reinforcement Learning by No-Regret Reduction
497. ICML 2023Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources
498. ICML 2023Provably Invariant Learning without Domain Information
499. ICML 2023Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL
500. ICML 2023QAS-Bench: Rethinking Quantum Architecture Search and A Benchmark

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。