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 1,640 篇，第 26 / 33 页

1251. NeurIPS 2025Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function
1252. NeurIPS 2025Multi-agent Markov Entanglement
1253. NeurIPS 2025Multi-Agent Reinforcement Learning with Communication-Constrained Priors
1254. NeurIPS 2025Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach
1255. NeurIPS 2025Multi-step Visual Reasoning with Visual Tokens Scaling and Verification
1256. NeurIPS 2025Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP
1257. NeurIPS 2025Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms
1258. NeurIPS 2025MURKA: Multi-Reward Reinforcement Learning with Knowledge Alignment for Optimization Tasks
1259. NeurIPS 2025MyoChallenge 2024: A New Benchmark for Physiological Dexterity and Agility in Bionic Humans
1260. NeurIPS 2025Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
1261. NeurIPS 2025NAVIX: Scaling MiniGrid Environments with JAX
1262. NeurIPS 2025Near-Optimal Sample Complexity for Online Constrained MDPs
1263. NeurIPS 2025NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning
1264. NeurIPS 2025Neural Combinatorial Optimization for Time Dependent Traveling Salesman Problem
1265. NeurIPS 2025No Experts, No Problem: Avoidance Learning from Bad Demonstrations
1266. NeurIPS 2025No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes
1267. NeurIPS 2025NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation
1268. NeurIPS 2025NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
1269. NeurIPS 2025Non-convex entropic mean-field optimization via Best Response flow
1270. NeurIPS 2025Non-rectangular Robust MDPs with Normed Uncertainty Sets
1271. NeurIPS 2025Normalizing Flows are Capable Models for Continuous Control
1272. NeurIPS 2025Novel Exploration via Orthogonality
1273. NeurIPS 2025NS-Gym: A Comprehensive and Open-Source Simulation Framework for Non-Stationary Markov Decision Processes
1274. NeurIPS 2025NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
1275. NeurIPS 2025Off-policy Reinforcement Learning with Model-based Exploration Augmentation
1276. NeurIPS 2025Offline Actor-Critic for Average Reward MDPs
1277. NeurIPS 2025Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations
1278. NeurIPS 2025Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies
1279. NeurIPS 2025Offline imitation learning in $Q^\pi$-realizable MDPs without expert realizability
1280. NeurIPS 2025Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
1281. NeurIPS 2025OMiSO: Adaptive optimization of state-dependent brain stimulation to shape neural population states
1282. NeurIPS 2025Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
1283. NeurIPS 2025On Evaluating Policies for Robust POMDPs
1284. NeurIPS 2025On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
1285. NeurIPS 2025On the Convergence of Single-Timescale Actor-Critic
1286. NeurIPS 2025On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
1287. NeurIPS 2025On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
1288. NeurIPS 2025On the Sample Complexity Bounds of Bilevel Reinforcement Learning
1289. NeurIPS 2025On the Sample Complexity of Differentially Private Policy Optimization
1290. NeurIPS 2025On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding
1291. NeurIPS 2025One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning
1292. NeurIPS 2025Online Optimization for Offline Safe Reinforcement Learning
1293. NeurIPS 2025Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
1294. NeurIPS 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
1295. NeurIPS 2025Open-World Drone Active Tracking with Goal-Centered Rewards
1296. NeurIPS 2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
1297. NeurIPS 2025OPHR: Mastering Volatility Trading with Multi-Agent Deep Reinforcement Learning
1298. NeurIPS 2025Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
1299. NeurIPS 2025Optimal Regret Bounds via Low-Rank Structured Variation in Non-Stationary Reinforcement Learning
1300. NeurIPS 2025Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL

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。