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 6,885 篇，第 137 / 138 页

6801. NeurIPS 2023Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation
6802. NeurIPS 2023SEENN: Towards Temporal Spiking Early Exit Neural Networks
6803. NeurIPS 2023Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning
6804. NeurIPS 2023Self-Predictive Universal AI
6805. NeurIPS 2023Self-Refine: Iterative Refinement with Self-Feedback
6806. NeurIPS 2023Self-Supervised Reinforcement Learning that Transfers using Random Features
6807. NeurIPS 2023Semantic HELM: A Human-Readable Memory for Reinforcement Learning
6808. NeurIPS 2023Sequential Preference Ranking for Efficient Reinforcement Learning from Human Feedback
6809. NeurIPS 2023SHOT: Suppressing the Hessian along the Optimization Trajectory for Gradient-Based Meta-Learning
6810. NeurIPS 2023SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
6811. NeurIPS 2023Small batch deep reinforcement learning
6812. NeurIPS 2023Social Motion Prediction with Cognitive Hierarchies
6813. NeurIPS 2023Solving a Class of Non-Convex Minimax Optimization in Federated Learning
6814. NeurIPS 2023Sorting with Predictions
6815. NeurIPS 2023Sparse Graph Learning from Spatiotemporal Time Series
6816. NeurIPS 2023Spatially Resolved Gene Expression Prediction from Histology Images via Bi-modal Contrastive Learning
6817. NeurIPS 2023Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning
6818. NeurIPS 2023SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning
6819. NeurIPS 2023SPRING: Studying Papers and Reasoning to play Games
6820. NeurIPS 2023State Regularized Policy Optimization on Data with Dynamics Shift
6821. NeurIPS 2023State Sequences Prediction via Fourier Transform for Representation Learning
6822. NeurIPS 2023State-Action Similarity-Based Representations for Off-Policy Evaluation
6823. NeurIPS 2023State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding
6824. NeurIPS 2023StateMask: Explaining Deep Reinforcement Learning through State Mask
6825. NeurIPS 2023STEVE-1: A Generative Model for Text-to-Behavior in Minecraft
6826. NeurIPS 2023Stochastic Approximation Approaches to Group Distributionally Robust Optimization
6827. NeurIPS 2023STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning
6828. NeurIPS 2023Strategic Apple Tasting
6829. NeurIPS 2023Structured State Space Models for In-Context Reinforcement Learning
6830. NeurIPS 2023Successor-Predecessor Intrinsic Exploration
6831. NeurIPS 2023Suggesting Variable Order for Cylindrical Algebraic Decomposition via Reinforcement Learning
6832. NeurIPS 2023Supervised Pretraining Can Learn In-Context Reinforcement Learning
6833. NeurIPS 2023Supported Value Regularization for Offline Reinforcement Learning
6834. NeurIPS 2023Survival Instinct in Offline Reinforcement Learning
6835. NeurIPS 2023SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems
6836. NeurIPS 2023Swarm Reinforcement Learning for Adaptive Mesh Refinement
6837. NeurIPS 2023Synthetic Experience Replay
6838. NeurIPS 2023T2T: From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization
6839. NeurIPS 2023Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds
6840. NeurIPS 2023Task-aware world model learning with meta weighting via bi-level optimization
6841. NeurIPS 2023TaskMet: Task-driven Metric Learning for Model Learning
6842. NeurIPS 2023Taylor TD-learning
6843. NeurIPS 2023TD Convergence: An Optimization Perspective
6844. NeurIPS 2023Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning
6845. NeurIPS 2023Tempo Adaptation in Non-stationary Reinforcement Learning
6846. NeurIPS 2023The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning
6847. NeurIPS 2023The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model
6848. NeurIPS 2023The Geometry of Neural Nets' Parameter Spaces Under Reparametrization
6849. NeurIPS 2023Thinker: Learning to Plan and Act
6850. NeurIPS 2023Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

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。