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 304 篇，第 6 / 7 页

251. ICLR 2024Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
252. ICLR 2024Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution
253. ICLR 2024Spatially-Aware Transformers for Embodied Agents
254. ICLR 2024SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
255. ICLR 2024Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
256. ICLR 2024STARC: A General Framework For Quantifying Differences Between Reward Functions
257. ICLR 2024Statistical Rejection Sampling Improves Preference Optimization
258. ICLR 2024Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets
259. ICLR 2024Submodular Reinforcement Learning
260. ICLR 2024SYMBOL: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
261. ICLR 2024Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning
262. ICLR 2024Task Planning for Visual Room Rearrangement under Partial Observability
263. ICLR 2024TD-MPC2: Scalable, Robust World Models for Continuous Control
264. ICLR 2024Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
265. ICLR 2024Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
266. ICLR 2024The Curse of Diversity in Ensemble-Based Exploration
267. ICLR 2024The Effective Horizon Explains Deep RL Performance in Stochastic Environments
268. ICLR 2024The Generalization Gap in Offline Reinforcement Learning
269. ICLR 2024The Trickle-down Impact of Reward Inconsistency on RLHF
270. ICLR 2024The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
271. ICLR 2024The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models
272. ICLR 2024Thin-Shell Object Manipulations With Differentiable Physics Simulations
273. ICLR 2024Time-Efficient Reinforcement Learning with Stochastic Stateful Policies
274. ICLR 2024Time-Varying Propensity Score to Bridge the Gap between the Past and Present
275. ICLR 2024Tool-Augmented Reward Modeling
276. ICLR 2024TorchRL: A data-driven decision-making library for PyTorch
277. ICLR 2024Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games
278. ICLR 2024Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
279. ICLR 2024Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach
280. ICLR 2024Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback
281. ICLR 2024Towards Principled Representation Learning from Videos for Reinforcement Learning
282. ICLR 2024Towards Robust Offline Reinforcement Learning under Diverse Data Corruption
283. ICLR 2024Towards Understanding Sycophancy in Language Models
284. ICLR 2024Training Diffusion Models with Reinforcement Learning
285. ICLR 2024Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
286. ICLR 2024Tree Search-Based Policy Optimization under Stochastic Execution Delay
287. ICLR 2024True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning
288. ICLR 2024Uncertainty-aware Constraint Inference in Inverse Constrained Reinforcement Learning
289. ICLR 2024Understanding Catastrophic Forgetting in Language Models via Implicit Inference
290. ICLR 2024Understanding the Effects of RLHF on LLM Generalisation and Diversity
291. ICLR 2024Understanding when Dynamics-Invariant Data Augmentations Benefit Model-free Reinforcement Learning Updates
292. ICLR 2024Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization
293. ICLR 2024Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback
294. ICLR 2024Universal Humanoid Motion Representations for Physics-Based Control
295. ICLR 2024Universal Jailbreak Backdoors from Poisoned Human Feedback
296. ICLR 2024Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
297. ICLR 2024Unlocking the Power of Representations in Long-term Novelty-based Exploration
298. ICLR 2024Unveiling Options with Neural Network Decomposition
299. ICLR 2024Vanishing Gradients in Reinforcement Finetuning of Language Models
300. ICLR 2024Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

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。