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 6,885 篇，第 133 / 138 页
- NeurIPS 2023Importance-aware Co-teaching for Offline Model-based Optimization
- NeurIPS 2023Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning
- NeurIPS 2023Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates
- NeurIPS 2023Inferring the Future by Imagining the Past
- NeurIPS 2023Information Design in Multi-Agent Reinforcement Learning
- NeurIPS 2023Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills
- NeurIPS 2023Instructing Goal-Conditioned Reinforcement Learning Agents with Temporal Logic Objectives
- NeurIPS 2023Interaction Measures, Partition Lattices and Kernel Tests for High-Order Interactions
- NeurIPS 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
- NeurIPS 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction
- NeurIPS 2023Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach
- NeurIPS 2023Inverse Preference Learning: Preference-based RL without a Reward Function
- NeurIPS 2023Inverse Reinforcement Learning with the Average Reward Criterion
- NeurIPS 2023Is RLHF More Difficult than Standard RL? A Theoretical Perspective
- NeurIPS 2023Iterative Reachability Estimation for Safe Reinforcement Learning
- NeurIPS 2023Iteratively Learn Diverse Strategies with State Distance Information
- NeurIPS 2023Katakomba: Tools and Benchmarks for Data-Driven NetHack
- NeurIPS 2023Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control
- NeurIPS 2023Kernelized Reinforcement Learning with Order Optimal Regret Bounds
- NeurIPS 2023Koopman Kernel Regression
- NeurIPS 2023KuaiSim: A Comprehensive Simulator for Recommender Systems
- NeurIPS 2023Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information
- NeurIPS 2023Language Model Alignment with Elastic Reset
- NeurIPS 2023Language Models can Solve Computer Tasks
- NeurIPS 2023Large Language Models Are Semi-Parametric Reinforcement Learning Agents
- NeurIPS 2023Large Language Models can Implement Policy Iteration
- NeurIPS 2023Latent exploration for Reinforcement Learning
- NeurIPS 2023Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback
- NeurIPS 2023Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning
- NeurIPS 2023Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning
- NeurIPS 2023Learning Exponential Families from Truncated Samples
- NeurIPS 2023Learning from Active Human Involvement through Proxy Value Propagation
- NeurIPS 2023Learning from Visual Observation via Offline Pretrained State-to-Go Transformer
- NeurIPS 2023Learning Generalizable Agents via Saliency-guided Features Decorrelation
- NeurIPS 2023Learning Multi-agent Behaviors from Distributed and Streaming Demonstrations
- NeurIPS 2023Learning non-Markovian Decision-Making from State-only Sequences
- NeurIPS 2023Learning Regularized Monotone Graphon Mean-Field Games
- NeurIPS 2023Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
- NeurIPS 2023Learning Shared Safety Constraints from Multi-task Demonstrations
- NeurIPS 2023Learning Space-Time Continuous Latent Neural PDEs from Partially Observed States
- NeurIPS 2023Learning the Efficient Frontier
- NeurIPS 2023Learning Time-Invariant Representations for Individual Neurons from Population Dynamics
- NeurIPS 2023Learning to Discover Skills through Guidance
- NeurIPS 2023Learning to Influence Human Behavior with Offline Reinforcement Learning
- NeurIPS 2023Learning to Modulate pre-trained Models in RL
- NeurIPS 2023Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt
- NeurIPS 2023Learning Unseen Modality Interaction
- NeurIPS 2023Learning World Models with Identifiable Factorization
- NeurIPS 2023Lending Interaction Wings to Recommender Systems with Conversational Agents
- NeurIPS 2023LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios
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。