强化学习论文趋势 2023–2026
策略优化、离线 RL 与基于环境的决策学习
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 6,885 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 484 | 233 | 297 | 56 | 1,070 |
| 2024 | 466 | 304 | 356 | 64 | 1,190 |
| 2025 | 784 | 379 | 405 | 72 | 1,640 |
| 2026 | 760 | 911 | 1,021 | 293 | 2,985 |
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 2,079 篇，第 24 / 42 页
- ICML 2025Extreme Value Policy Optimization for Safe Reinforcement Learning
- ICML 2025Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
- ICML 2025Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games
- ICML 2025Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
- ICML 2025Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
- ICML 2025Flow Q-Learning
- ICML 2025Flow-based Domain Randomization for Learning and Sequencing Robotic Skills
- ICML 2025Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
- ICML 2025FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
- ICML 2025Gap-Dependent Bounds for Federated $Q$-Learning
- ICML 2025General agents need world models
- ICML 2025GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation
- ICML 2025Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
- ICML 2025GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction
- ICML 2025Gradient Boosting Reinforcement Learning
- ICML 2025GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning
- ICML 2025Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
- ICML 2025GRAM: A Generative Foundation Reward Model for Reward Generalization
- ICML 2025Graph Diffusion for Robust Multi-Agent Coordination
- ICML 2025Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning
- ICML 2025Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization
- ICML 2025Guided Zeroth-Order Methods for Stochastic Non-convex Problems with Decision-Dependent Distributions
- ICML 2025Habitizing Diffusion Planning for Efficient and Effective Decision Making
- ICML 2025Hierarchical Reinforcement Learning with Targeted Causal Interventions
- ICML 2025Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals
- ICML 2025High-Dimensional Prediction for Sequential Decision Making
- ICML 2025How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction
- ICML 2025HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning
- ICML 2025Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning
- ICML 2025Hyperspherical Normalization for Scalable Deep Reinforcement Learning
- ICML 2025IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic
- ICML 2025Imitation Learning from a Single Temporally Misaligned Video
- ICML 2025Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling
- ICML 2025Improved Off-policy Reinforcement Learning in Biological Sequence Design
- ICML 2025Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces
- ICML 2025Improving Reward Model Generalization from Adversarial Process Enhanced Preferences
- ICML 2025Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning
- ICML 2025Improving Transformer World Models for Data-Efficient RL
- ICML 2025Improving Value Estimation Critically Enhances Vanilla Policy Gradient
- ICML 2025In-Context Reinforcement Learning From Suboptimal Historical Data
- ICML 2025Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games
- ICML 2025Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning
- ICML 2025Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces
- ICML 2025Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors
- ICML 2025Investigating the Overlooked Hessian Structure: From CNNs to LLMs
- ICML 2025Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
- ICML 2025KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies
- ICML 2025Knowledge Retention in Continual Model-Based Reinforcement Learning
- ICML 2025LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
- ICML 2025Language Models as Implicit Tree Search
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查强化学习在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "reinforcement-learning"}
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。