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 13 / 24 页

601. ICML 2024Position: Insights from Survey Methodology can Improve Training Data
602. ICML 2024Position: Leverage Foundational Models for Black-Box Optimization
603. ICML 2024Position: Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination
604. ICML 2024Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback
605. ICML 2024Position: Social Environment Design Should be Further Developed for AI-based Policy-Making
606. ICML 2024Position: Video as the New Language for Real-World Decision Making
607. ICML 2024Predictive Performance Comparison of Decision Policies Under Confounding
608. ICML 2024Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
609. ICML 2024Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF
610. ICML 2024Privacy-Preserving Instructions for Aligning Large Language Models
611. ICML 2024Probabilistic Constrained Reinforcement Learning with Formal Interpretability
612. ICML 2024Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
613. ICML 2024Probabilistic Subgoal Representations for Hierarchical Reinforcement Learning
614. ICML 2024Profile Reconstruction from Private Sketches
615. ICML 2024Prompt-based Visual Alignment for Zero-shot Policy Transfer
616. ICML 2024Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning
617. ICML 2024Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation
618. ICML 2024Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret
619. ICML 2024Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation
620. ICML 2024Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback
621. ICML 2024Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
622. ICML 2024Q-value Regularized Transformer for Offline Reinforcement Learning
623. ICML 2024QORA: Zero-Shot Transfer via Interpretable Object-Relational Model Learning
624. ICML 2024Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization
625. ICML 2024Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics
626. ICML 2024Quality-Diversity with Limited Resources
627. ICML 2024Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design
628. ICML 2024Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency
629. ICML 2024Random Latent Exploration for Deep Reinforcement Learning
630. ICML 2024Rate-Optimal Policy Optimization for Linear Markov Decision Processes
631. ICML 2024Recovering Labels from Local Updates in Federated Learning
632. ICML 2024ReDiffuser: Reliable Decision-Making Using a Diffuser with Confidence Estimation
633. ICML 2024Refining Minimax Regret for Unsupervised Environment Design
634. ICML 2024Reflective Policy Optimization
635. ICML 2024Reinforcement Learning and Regret Bounds for Admission Control
636. ICML 2024Reinforcement Learning from Reachability Specifications: PAC Guarantees with Expected Conditional Distance
637. ICML 2024Reinforcement Learning within Tree Search for Fast Macro Placement
638. ICML 2024Reinformer: Max-Return Sequence Modeling for Offline RL
639. ICML 2024ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
640. ICML 2024ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
641. ICML 2024Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making
642. ICML 2024Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation
643. ICML 2024Rethinking Decision Transformer via Hierarchical Reinforcement Learning
644. ICML 2024Rethinking Transformers in Solving POMDPs
645. ICML 2024Revisiting Inexact Fixed-Point Iterations for Min-Max Problems: Stochasticity and Structured Nonconvexity
646. ICML 2024Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
647. ICML 2024Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
648. ICML 2024Reward Shaping for Reinforcement Learning with An Assistant Reward Agent
649. ICML 2024Reward-Free Kernel-Based Reinforcement Learning
650. ICML 2024Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

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。