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 1,070 篇，第 4 / 22 页

151. ICLR 2023Improving Deep Policy Gradients with Value Function Search
152. ICLR 2023In-context Reinforcement Learning with Algorithm Distillation
153. ICLR 2023In-sample Actor Critic for Offline Reinforcement Learning
154. ICLR 2023Interaction-Based Disentanglement of Entities for Object-Centric World Models
155. ICLR 2023Investigating Multi-task Pretraining and Generalization in Reinforcement Learning
156. ICLR 2023Is Conditional Generative Modeling all you need for Decision Making?
157. ICLR 2023Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function
158. ICLR 2023Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
159. ICLR 2023Latent State Marginalization as a Low-cost Approach for Improving Exploration
160. ICLR 2023Latent Variable Representation for Reinforcement Learning
161. ICLR 2023Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
162. ICLR 2023Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering
163. ICLR 2023Learning About Progress From Experts
164. ICLR 2023Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward
165. ICLR 2023Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition
166. ICLR 2023Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model
167. ICLR 2023Learning Simultaneous Navigation and Construction in Grid Worlds
168. ICLR 2023Learning Soft Constraints From Constrained Expert Demonstrations
169. ICLR 2023Learning to Segment from Noisy Annotations: A Spatial Correction Approach
170. ICLR 2023Learning Uncertainty for Unknown Domains with Zero-Target-Assumption
171. ICLR 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
172. ICLR 2023Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies
173. ICLR 2023LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning
174. ICLR 2023MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection
175. ICLR 2023MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
176. ICLR 2023Making Better Decision by Directly Planning in Continuous Control
177. ICLR 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
178. ICLR 2023Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning
179. ICLR 2023Memory Gym: Partially Observable Challenges to Memory-Based Agents
180. ICLR 2023Mind the Gap: Offline Policy Optimization for Imperfect Rewards
181. ICLR 2023Minimax Optimal Kernel Operator Learning via Multilevel Training
182. ICLR 2023Minimum Description Length Control
183. ICLR 2023Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach
184. ICLR 2023MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
185. ICLR 2023More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization
186. ICLR 2023Multi-Objective Reinforcement Learning: Convexity, Stationarity and Pareto Optimality
187. ICLR 2023Multi-skill Mobile Manipulation for Object Rearrangement
188. ICLR 2023Near-Optimal Adversarial Reinforcement Learning with Switching Costs
189. ICLR 2023Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation
190. ICLR 2023Near-optimal Policy Identification in Active Reinforcement Learning
191. ICLR 2023Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game
192. ICLR 2023Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication
193. ICLR 2023Neural DAG Scheduling via One-Shot Priority Sampling
194. ICLR 2023Neural Episodic Control with State Abstraction
195. ICLR 2023Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery
196. ICLR 2023Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes
197. ICLR 2023Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling
198. ICLR 2023Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient
199. ICLR 2023Offline RL for Natural Language Generation with Implicit Language Q Learning
200. ICLR 2023Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization

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。