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 15 / 24 页

701. ICML 2024To the Max: Reinventing Reward in Reinforcement Learning
702. ICML 2024Towards Efficient Exact Optimization of Language Model Alignment
703. ICML 2024Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph
704. ICML 2024Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles
705. ICML 2024Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
706. ICML 2024Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption
707. ICML 2024Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization
708. ICML 2024Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
709. ICML 2024Truly No-Regret Learning in Constrained MDPs
710. ICML 2024Trust the Model Where It Trusts Itself - Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption
711. ICML 2024Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning
712. ICML 2024ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback
713. ICML 2024Uncertainty-Aware Reward-Free Exploration with General Function Approximation
714. ICML 2024Understanding and Diagnosing Deep Reinforcement Learning
715. ICML 2024Unlock the Cognitive Generalization of Deep Reinforcement Learning via Granular Ball Representation
716. ICML 2024Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
717. ICML 2024Value-Evolutionary-Based Reinforcement Learning
718. ICML 2024WARM: On the Benefits of Weight Averaged Reward Models
719. ICML 2024Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
720. ICML 2024When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions
721. ICML 2024When is Transfer Learning Possible?
722. ICML 2024Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning
723. ICML 2024Zero-Shot Reinforcement Learning via Function Encoders
724. ICML 2024Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach
725. NeurIPS 2024A Critical Evaluation of AI Feedback for Aligning Large Language Models
726. NeurIPS 2024A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
727. NeurIPS 2024A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
728. NeurIPS 2024A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics
729. NeurIPS 2024A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations
730. NeurIPS 2024A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data
731. NeurIPS 2024A Structure-Aware Framework for Learning Device Placements on Computation Graphs
732. NeurIPS 2024A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
733. NeurIPS 2024A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning
734. NeurIPS 2024A Tractable Inference Perspective of Offline RL
735. NeurIPS 2024A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch
736. NeurIPS 2024A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective
737. NeurIPS 2024Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation
738. NeurIPS 2024Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process
739. NeurIPS 2024Achieving Constant Regret in Linear Markov Decision Processes
740. NeurIPS 2024Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
741. NeurIPS 2024Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
742. NeurIPS 2024Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps
743. NeurIPS 2024Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning
744. NeurIPS 2024Adaptive Exploration for Data-Efficient General Value Function Evaluations
745. NeurIPS 2024Adaptive Labeling for Efficient Out-of-distribution Model Evaluation
746. NeurIPS 2024Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
747. NeurIPS 2024AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection
748. NeurIPS 2024AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
749. NeurIPS 2024ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
750. NeurIPS 2024Adversarial Environment Design via Regret-Guided Diffusion 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。