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 12 / 24 页

551. ICML 2024Model-based Reinforcement Learning for Parameterized Action Spaces
552. ICML 2024Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL
553. ICML 2024Model-Free Robust $\phi$-Divergence Reinforcement Learning Using Both Offline and Online Data
554. ICML 2024Mollification Effects of Policy Gradient Methods
555. ICML 2024Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments
556. ICML 2024More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning
557. ICML 2024Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy
558. ICML 2024Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder Stationing
559. ICML 2024Multi-View Clustering by Inter-cluster Connectivity Guided Reward
560. ICML 2024MusicRL: Aligning Music Generation to Human Preferences
561. ICML 2024Nash Learning from Human Feedback
562. ICML 2024Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback
563. ICML 2024Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints
564. ICML 2024Neural-Kernel Conditional Mean Embeddings
565. ICML 2024No-Regret Reinforcement Learning in Smooth MDPs
566. ICML 2024Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation
567. ICML 2024Nonlinear Filtering with Brenier Optimal Transport Maps
568. ICML 2024ODIN: Disentangled Reward Mitigates Hacking in RLHF
569. ICML 2024Offline Actor-Critic Reinforcement Learning Scales to Large Models
570. ICML 2024Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching
571. ICML 2024Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms
572. ICML 2024Offline Multi-Objective Optimization
573. ICML 2024Offline Transition Modeling via Contrastive Energy Learning
574. ICML 2024Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL
575. ICML 2024OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning
576. ICML 2024OMPO: A Unified Framework for RL under Policy and Dynamics Shifts
577. ICML 2024On the Second-Order Convergence of Biased Policy Gradient Algorithms
578. ICML 2024On The Statistical Complexity of Offline Decision-Making
579. ICML 2024On the Unexpected Effectiveness of Reinforcement Learning for Sequential Recommendation
580. ICML 2024On Which Nodes Does GCN Fail? Enhancing GCN From the Node Perspective
581. ICML 2024Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement Learning
582. ICML 2024Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization
583. ICML 2024OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos
584. ICML 2024Overcoming the Optimizer's Curse: Obtaining Realistic Prescriptions from Neural Networks
585. ICML 2024Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
586. ICML 2024Parameter Estimation in DAGs from Incomplete Data via Optimal Transport
587. ICML 2024Pausing Policy Learning in Non-stationary Reinforcement Learning
588. ICML 2024PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
589. ICML 2024Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning
590. ICML 2024Pi-DUAL: Using privileged information to distinguish clean from noisy labels
591. ICML 2024PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning
592. ICML 2024PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling
593. ICML 2024PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer
594. ICML 2024Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners
595. ICML 2024Policy Evaluation for Variance in Average Reward Reinforcement Learning
596. ICML 2024Policy Learning for Balancing Short-Term and Long-Term Rewards
597. ICML 2024Policy-conditioned Environment Models are More Generalizable
598. ICML 2024Position: Amazing Things Come From Having Many Good Models
599. ICML 2024Position: Automatic Environment Shaping is the Next Frontier in RL
600. ICML 2024Position: Benchmarking is Limited in Reinforcement Learning Research

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。