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 2,079 篇，第 35 / 42 页

1701. ICML 2024Rethinking Decision Transformer via Hierarchical Reinforcement Learning
1702. ICML 2024Rethinking Transformers in Solving POMDPs
1703. ICML 2024Revisiting Inexact Fixed-Point Iterations for Min-Max Problems: Stochasticity and Structured Nonconvexity
1704. ICML 2024Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
1705. ICML 2024Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
1706. ICML 2024Reward Shaping for Reinforcement Learning with An Assistant Reward Agent
1707. ICML 2024Reward-Free Kernel-Based Reinforcement Learning
1708. ICML 2024Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
1709. ICML 2024RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
1710. ICML 2024Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
1711. ICML 2024RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences
1712. ICML 2024Risk-Sensitive Policy Optimization via Predictive CVaR Policy Gradient
1713. ICML 2024Risk-Sensitive Reward-Free Reinforcement Learning with CVaR
1714. ICML 2024RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning
1715. ICML 2024RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback
1716. ICML 2024RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
1717. ICML 2024RLVF: Learning from Verbal Feedback without Overgeneralization
1718. ICML 2024RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
1719. ICML 2024Robust Inverse Constrained Reinforcement Learning under Model Misspecification
1720. ICML 2024Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space
1721. ICML 2024Run-Time Task Composition with Safety Semantics
1722. ICML 2024RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning
1723. ICML 2024Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
1724. ICML 2024Sample Average Approximation for Conditional Stochastic Optimization with Dependent Data
1725. ICML 2024Sample-Efficient Multiagent Reinforcement Learning with Reset Replay
1726. ICML 2024Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty
1727. ICML 2024SAPG: Split and Aggregate Policy Gradients
1728. ICML 2024Scalable Multiple Kernel Clustering: Learning Clustering Structure from Expectation
1729. ICML 2024Scalable Online Exploration via Coverability
1730. ICML 2024Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic
1731. ICML 2024Self-Composing Policies for Scalable Continual Reinforcement Learning
1732. ICML 2024SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets
1733. ICML 2024Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning
1734. ICML 2024Sequential Asynchronous Action Coordination in Multi-Agent Systems: A Stackelberg Decision Transformer Approach
1735. ICML 2024SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
1736. ICML 2024SHINE: Shielding Backdoors in Deep Reinforcement Learning
1737. ICML 2024Simple Ingredients for Offline Reinforcement Learning
1738. ICML 2024Single-Trajectory Distributionally Robust Reinforcement Learning
1739. ICML 2024SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning
1740. ICML 2024Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
1741. ICML 2024Smooth Min-Max Monotonic Networks
1742. ICML 2024Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach
1743. ICML 2024Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms
1744. ICML 2024Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process
1745. ICML 2024Stealthy Imitation: Reward-guided Environment-free Policy Stealing
1746. ICML 2024Stochastic Q-learning for Large Discrete Action Spaces
1747. ICML 2024Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
1748. ICML 2024Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments
1749. ICML 2024Subgoal-based Demonstration Learning for Formal Theorem Proving
1750. ICML 2024Successor Features for Efficient Multi-Subject Controlled Text Generation

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。