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 466 篇，第 6 / 10 页

251. NeurIPS 2024MiSO: Optimizing brain stimulation to create neural activity states
252. NeurIPS 2024Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction
253. NeurIPS 2024Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy
254. NeurIPS 2024Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation
255. NeurIPS 2024Model-based Diffusion for Trajectory Optimization
256. NeurIPS 2024Model-Based Transfer Learning for Contextual Reinforcement Learning
257. NeurIPS 2024Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation
258. NeurIPS 2024MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training
259. NeurIPS 2024Multi-Agent Coordination via Multi-Level Communication
260. NeurIPS 2024Multi-Agent Domain Calibration with a Handful of Offline Data
261. NeurIPS 2024Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
262. NeurIPS 2024Multi-Reward Best Policy Identification
263. NeurIPS 2024Multi-turn Reinforcement Learning with Preference Human Feedback
264. NeurIPS 2024Multimodal Large Language Models Make Text-to-Image Generative Models Align Better
265. NeurIPS 2024Mutli-Armed Bandits with Network Interference
266. NeurIPS 2024N-agent Ad Hoc Teamwork
267. NeurIPS 2024Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
268. NeurIPS 2024Near-Optimal Distributionally Robust Reinforcement Learning with General $L_p$ Norms
269. NeurIPS 2024Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
270. NeurIPS 2024NeoRL: Efficient Exploration for Nonepisodic RL
271. NeurIPS 2024NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
272. NeurIPS 2024Neural Combinatorial Optimization for Robust Routing Problem with Uncertain Travel Times
273. NeurIPS 2024NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning
274. NeurIPS 2024No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
275. NeurIPS 2024No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO
276. NeurIPS 2024Noise Contrastive Alignment of Language Models with Explicit Rewards
277. NeurIPS 2024Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation
278. NeurIPS 2024Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
279. NeurIPS 2024Normalization and effective learning rates in reinforcement learning
280. NeurIPS 2024OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
281. NeurIPS 2024Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
282. NeurIPS 2024ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
283. NeurIPS 2024Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
284. NeurIPS 2024Off-policy estimation with adaptively collected data: the power of online learning
285. NeurIPS 2024Off-Policy Selection for Initiating Human-Centric Experimental Design
286. NeurIPS 2024Offline Behavior Distillation
287. NeurIPS 2024Offline Multitask Representation Learning for Reinforcement Learning
288. NeurIPS 2024Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
289. NeurIPS 2024Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
290. NeurIPS 2024OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
291. NeurIPS 2024On the Complexity of Teaching a Family of Linear Behavior Cloning Learners
292. NeurIPS 2024On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
293. NeurIPS 2024On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games
294. NeurIPS 2024One-Shot Safety Alignment for Large Language Models via Optimal Dualization
295. NeurIPS 2024Online Control with Adversarial Disturbance for Continuous-time Linear Systems
296. NeurIPS 2024Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
297. NeurIPS 2024OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
298. NeurIPS 2024Operator World Models for Reinforcement Learning
299. NeurIPS 2024Opponent Modeling based on Subgoal Inference
300. NeurIPS 2024Opponent Modeling with In-context Search

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。