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 297 篇，第 6 / 6 页

251. ICML 2023Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments
252. ICML 2023Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search
253. ICML 2023Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning
254. ICML 2023Simplified Temporal Consistency Reinforcement Learning
255. ICML 2023SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning
256. ICML 2023Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning
257. ICML 2023STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning
258. ICML 2023Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
259. ICML 2023STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition
260. ICML 2023StriderNet: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes
261. ICML 2023Subequivariant Graph Reinforcement Learning in 3D Environments
262. ICML 2023Supported Trust Region Optimization for Offline Reinforcement Learning
263. ICML 2023Target-based Surrogates for Stochastic Optimization
264. ICML 2023TGRL: An Algorithm for Teacher Guided Reinforcement Learning
265. ICML 2023The Benefits of Model-Based Generalization in Reinforcement Learning
266. ICML 2023The Dormant Neuron Phenomenon in Deep Reinforcement Learning
267. ICML 2023The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation
268. ICML 2023The Regret of Exploration and the Control of Bad Episodes in Reinforcement Learning
269. ICML 2023The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation
270. ICML 2023The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
271. ICML 2023The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
272. ICML 2023The Wisdom of Hindsight Makes Language Models Better Instruction Followers
273. ICML 2023Tighter Information-Theoretic Generalization Bounds from Supersamples
274. ICML 2023Toward Efficient Gradient-Based Value Estimation
275. ICML 2023Towards a better understanding of representation dynamics under TD-learning
276. ICML 2023Towards Learning to Imitate from a Single Video Demonstration
277. ICML 2023Towards Robust and Safe Reinforcement Learning with Benign Off-policy Data
278. ICML 2023Towards Theoretical Understanding of Inverse Reinforcement Learning
279. ICML 2023Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
280. ICML 2023Truncating Trajectories in Monte Carlo Reinforcement Learning
281. ICML 2023Tuning Computer Vision Models With Task Rewards
282. ICML 2023Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy
283. ICML 2023Understanding and Generalizing Contrastive Learning from the Inverse Optimal Transport Perspective
284. ICML 2023Understanding Plasticity in Neural Networks
285. ICML 2023Understanding Self-Predictive Learning for Reinforcement Learning
286. ICML 2023Understanding the Complexity Gains of Single-Task RL with a Curriculum
287. ICML 2023Universal Morphology Control via Contextual Modulation
288. ICML 2023VA-learning as a more efficient alternative to Q-learning
289. ICML 2023Variance Control for Distributional Reinforcement Learning
290. ICML 2023Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills
291. ICML 2023VectorMapNet: End-to-end Vectorized HD Map Learning
292. ICML 2023Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap
293. ICML 2023Weighted Sampling without Replacement for Deep Top-$k$ Classification
294. ICML 2023What can online reinforcement learning with function approximation benefit from general coverage conditions?
295. ICML 2023What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?
296. ICML 2023When is Realizability Sufficient for Off-Policy Reinforcement Learning?
297. ICML 2023Why Target Networks Stabilise Temporal Difference Methods

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。