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 2,494 篇，第 45 / 50 页

2201. NeurIPS 2023Hybrid Policy Optimization from Imperfect Demonstrations
2202. NeurIPS 2023Hybrid Search for Efficient Planning with Completeness Guarantees
2203. NeurIPS 2023Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels
2204. NeurIPS 2023Hyperbolic VAE via Latent Gaussian Distributions
2205. NeurIPS 2023Hypervolume Maximization: A Geometric View of Pareto Set Learning
2206. NeurIPS 2023Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
2207. NeurIPS 2023Imitation Learning from Vague Feedback
2208. NeurIPS 2023IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL
2209. NeurIPS 2023Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning
2210. NeurIPS 2023Importance-aware Co-teaching for Offline Model-based Optimization
2211. NeurIPS 2023Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning
2212. NeurIPS 2023Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates
2213. NeurIPS 2023Inferring the Future by Imagining the Past
2214. NeurIPS 2023Information Design in Multi-Agent Reinforcement Learning
2215. NeurIPS 2023Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills
2216. NeurIPS 2023Instructing Goal-Conditioned Reinforcement Learning Agents with Temporal Logic Objectives
2217. NeurIPS 2023Interaction Measures, Partition Lattices and Kernel Tests for High-Order Interactions
2218. NeurIPS 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
2219. NeurIPS 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction
2220. NeurIPS 2023Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach
2221. NeurIPS 2023Inverse Preference Learning: Preference-based RL without a Reward Function
2222. NeurIPS 2023Inverse Reinforcement Learning with the Average Reward Criterion
2223. NeurIPS 2023Is RLHF More Difficult than Standard RL? A Theoretical Perspective
2224. NeurIPS 2023Iterative Reachability Estimation for Safe Reinforcement Learning
2225. NeurIPS 2023Iteratively Learn Diverse Strategies with State Distance Information
2226. NeurIPS 2023Katakomba: Tools and Benchmarks for Data-Driven NetHack
2227. NeurIPS 2023Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control
2228. NeurIPS 2023Kernelized Reinforcement Learning with Order Optimal Regret Bounds
2229. NeurIPS 2023Koopman Kernel Regression
2230. NeurIPS 2023KuaiSim: A Comprehensive Simulator for Recommender Systems
2231. NeurIPS 2023Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information
2232. NeurIPS 2023Language Model Alignment with Elastic Reset
2233. NeurIPS 2023Language Models can Solve Computer Tasks
2234. NeurIPS 2023Large Language Models Are Semi-Parametric Reinforcement Learning Agents
2235. NeurIPS 2023Large Language Models can Implement Policy Iteration
2236. NeurIPS 2023Latent exploration for Reinforcement Learning
2237. NeurIPS 2023Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback
2238. NeurIPS 2023Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning
2239. NeurIPS 2023Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning
2240. NeurIPS 2023Learning Exponential Families from Truncated Samples
2241. NeurIPS 2023Learning from Active Human Involvement through Proxy Value Propagation
2242. NeurIPS 2023Learning from Visual Observation via Offline Pretrained State-to-Go Transformer
2243. NeurIPS 2023Learning Generalizable Agents via Saliency-guided Features Decorrelation
2244. NeurIPS 2023Learning Multi-agent Behaviors from Distributed and Streaming Demonstrations
2245. NeurIPS 2023Learning non-Markovian Decision-Making from State-only Sequences
2246. NeurIPS 2023Learning Regularized Monotone Graphon Mean-Field Games
2247. NeurIPS 2023Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
2248. NeurIPS 2023Learning Shared Safety Constraints from Multi-task Demonstrations
2249. NeurIPS 2023Learning Space-Time Continuous Latent Neural PDEs from Partially Observed States
2250. NeurIPS 2023Learning the Efficient Frontier

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。