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 1,190 篇，第 9 / 24 页

401. ICML 2024Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays
402. ICML 2024BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
403. ICML 2024Breadth-First Exploration on Adaptive Grid for Reinforcement Learning
404. ICML 2024Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
405. ICML 2024Bridging Environments and Language with Rendering Functions and Vision-Language Models
406. ICML 2024Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
407. ICML 2024Code as Reward: Empowering Reinforcement Learning with VLMs
408. ICML 2024CogBench: a large language model walks into a psychology lab
409. ICML 2024Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond
410. ICML 2024Combining Experimental and Historical Data for Policy Evaluation
411. ICML 2024Confidence Aware Inverse Constrained Reinforcement Learning
412. ICML 2024Constrained Ensemble Exploration for Unsupervised Skill Discovery
413. ICML 2024Constrained Reinforcement Learning Under Model Mismatch
414. ICML 2024Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning
415. ICML 2024Controlled Decoding from Language Models
416. ICML 2024Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
417. ICML 2024Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation
418. ICML 2024Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
419. ICML 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatch
420. ICML 2024Dealing With Unbounded Gradients in Stochastic Saddle-point Optimization
421. ICML 2024Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
422. ICML 2024Decoding-time Realignment of Language Models
423. ICML 2024Decoupling Learning and Decision-Making: Breaking the $\mathcal{O}(\sqrt{T})$ Barrier in Online Resource Allocation with First-Order Methods
424. ICML 2024Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single Demonstration
425. ICML 2024Degeneration-free Policy Optimization: RL Fine-Tuning for Language Models without Degeneration
426. ICML 2024Dense Reward for Free in Reinforcement Learning from Human Feedback
427. ICML 2024Detecting Influence Structures in Multi-Agent Reinforcement Learning
428. ICML 2024DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching
429. ICML 2024Discovering Features with Synergistic Interactions in Multiple Views
430. ICML 2024Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning
431. ICML 2024Distinguishing the Knowable from the Unknowable with Language Models
432. ICML 2024Distributional Bellman Operators over Mean Embeddings
433. ICML 2024Do Transformer World Models Give Better Policy Gradients?
434. ICML 2024DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing Problems
435. ICML 2024Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming
436. ICML 2024DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design
437. ICML 2024DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems
438. ICML 2024ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance
439. ICML 2024Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning
440. ICML 2024Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling
441. ICML 2024Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design
442. ICML 2024Efficient World Models with Context-Aware Tokenization
443. ICML 2024EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data
444. ICML 2024Emergence of In-Context Reinforcement Learning from Noise Distillation
445. ICML 2024End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations
446. ICML 2024Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning
447. ICML 2024Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning
448. ICML 2024Environment Design for Inverse Reinforcement Learning
449. ICML 2024EvIL: Evolution Strategies for Generalisable Imitation Learning
450. ICML 2024EvoRainbow: Combining Improvements in Evolutionary Reinforcement Learning for Policy 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。