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 466 篇，第 9 / 10 页

401. NeurIPS 2024Speculative Monte-Carlo Tree Search
402. NeurIPS 2024SPO: Sequential Monte Carlo Policy Optimisation
403. NeurIPS 2024SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning
404. NeurIPS 2024State Chrono Representation for Enhancing Generalization in Reinforcement Learning
405. NeurIPS 2024State-free Reinforcement Learning
406. NeurIPS 2024Statistical Efficiency of Distributional Temporal Difference Learning
407. NeurIPS 2024Stepwise Alignment for Constrained Language Model Policy Optimization
408. NeurIPS 2024Stress-Testing Capability Elicitation With Password-Locked Models
409. NeurIPS 2024Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning
410. NeurIPS 2024Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning
411. NeurIPS 2024Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
412. NeurIPS 2024SurgicAI: A Hierarchical Platform for Fine-Grained Surgical Policy Learning and Benchmarking
413. NeurIPS 2024SustainDC: Benchmarking for Sustainable Data Center Control
414. NeurIPS 2024Swift Sampler: Efficient Learning of Sampler by 10 Parameters
415. NeurIPS 2024Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale
416. NeurIPS 2024Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
417. NeurIPS 2024Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games
418. NeurIPS 2024Temporal-Difference Learning Using Distributed Error Signals
419. NeurIPS 2024Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
420. NeurIPS 2024Text-Aware Diffusion for Policy Learning
421. NeurIPS 2024The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization
422. NeurIPS 2024The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
423. NeurIPS 2024The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
424. NeurIPS 2024The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space
425. NeurIPS 2024The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
426. NeurIPS 2024The Power of Resets in Online Reinforcement Learning
427. NeurIPS 2024The Sample-Communication Complexity Trade-off in Federated Q-Learning
428. NeurIPS 2024The surprising efficiency of temporal difference learning for rare event prediction
429. NeurIPS 2024The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning
430. NeurIPS 2024The Value of Reward Lookahead in Reinforcement Learning
431. NeurIPS 2024Time-Constrained Robust MDPs
432. NeurIPS 2024Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning
433. NeurIPS 2024Towards Effective Planning Strategies for Dynamic Opinion Networks
434. NeurIPS 2024Towards Next-Generation Logic Synthesis: A Scalable Neural Circuit Generation Framework
435. NeurIPS 2024Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning
436. NeurIPS 2024Towards Visual Text Design Transfer Across Languages
437. NeurIPS 2024Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\pi$-Realizability and Concentrability
438. NeurIPS 2024Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
439. NeurIPS 2024Transition Constrained Bayesian Optimization via Markov Decision Processes
440. NeurIPS 2024Truncated Variance Reduced Value Iteration
441. NeurIPS 2024TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models
442. NeurIPS 2024Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning
443. NeurIPS 2024UltraMedical: Building Specialized Generalists in Biomedicine
444. NeurIPS 2024Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions
445. NeurIPS 2024Understanding and Improving Training-free Loss-based Diffusion Guidance
446. NeurIPS 2024Understanding Model Selection for Learning in Strategic Environments
447. NeurIPS 2024Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning
448. NeurIPS 2024Unlock the Intermittent Control Ability of Model Free Reinforcement Learning
449. NeurIPS 2024Using Unity to Help Solve Reinforcement Learning
450. NeurIPS 2024Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training

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。