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 356 篇，第 7 / 8 页

301. ICML 2024SAPG: Split and Aggregate Policy Gradients
302. ICML 2024Scalable Multiple Kernel Clustering: Learning Clustering Structure from Expectation
303. ICML 2024Scalable Online Exploration via Coverability
304. ICML 2024Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic
305. ICML 2024Self-Composing Policies for Scalable Continual Reinforcement Learning
306. ICML 2024SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets
307. ICML 2024Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning
308. ICML 2024Sequential Asynchronous Action Coordination in Multi-Agent Systems: A Stackelberg Decision Transformer Approach
309. ICML 2024SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
310. ICML 2024SHINE: Shielding Backdoors in Deep Reinforcement Learning
311. ICML 2024Simple Ingredients for Offline Reinforcement Learning
312. ICML 2024Single-Trajectory Distributionally Robust Reinforcement Learning
313. ICML 2024SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning
314. ICML 2024Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
315. ICML 2024Smooth Min-Max Monotonic Networks
316. ICML 2024Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach
317. ICML 2024Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms
318. ICML 2024Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process
319. ICML 2024Stealthy Imitation: Reward-guided Environment-free Policy Stealing
320. ICML 2024Stochastic Q-learning for Large Discrete Action Spaces
321. ICML 2024Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
322. ICML 2024Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments
323. ICML 2024Subgoal-based Demonstration Learning for Formal Theorem Proving
324. ICML 2024Successor Features for Efficient Multi-Subject Controlled Text Generation
325. ICML 2024Switching the Loss Reduces the Cost in Batch Reinforcement Learning
326. ICML 2024Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization
327. ICML 2024Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation
328. ICML 2024Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation
329. ICML 2024Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning
330. ICML 2024Test-Time Regret Minimization in Meta Reinforcement Learning
331. ICML 2024The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm
332. ICML 2024The Non-linear $F$-Design and Applications to Interactive Learning
333. ICML 2024To the Max: Reinventing Reward in Reinforcement Learning
334. ICML 2024Towards Efficient Exact Optimization of Language Model Alignment
335. ICML 2024Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph
336. ICML 2024Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles
337. ICML 2024Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
338. ICML 2024Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption
339. ICML 2024Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization
340. ICML 2024Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
341. ICML 2024Truly No-Regret Learning in Constrained MDPs
342. ICML 2024Trust the Model Where It Trusts Itself - Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption
343. ICML 2024Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning
344. ICML 2024ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback
345. ICML 2024Uncertainty-Aware Reward-Free Exploration with General Function Approximation
346. ICML 2024Understanding and Diagnosing Deep Reinforcement Learning
347. ICML 2024Unlock the Cognitive Generalization of Deep Reinforcement Learning via Granular Ball Representation
348. ICML 2024Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
349. ICML 2024Value-Evolutionary-Based Reinforcement Learning
350. ICML 2024WARM: On the Benefits of Weight Averaged Reward Models

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。