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 121 / 138 页

6001. ICLR 2023Multi-Objective Reinforcement Learning: Convexity, Stationarity and Pareto Optimality
6002. ICLR 2023Multi-skill Mobile Manipulation for Object Rearrangement
6003. ICLR 2023Near-Optimal Adversarial Reinforcement Learning with Switching Costs
6004. ICLR 2023Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation
6005. ICLR 2023Near-optimal Policy Identification in Active Reinforcement Learning
6006. ICLR 2023Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game
6007. ICLR 2023Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication
6008. ICLR 2023Neural DAG Scheduling via One-Shot Priority Sampling
6009. ICLR 2023Neural Episodic Control with State Abstraction
6010. ICLR 2023Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery
6011. ICLR 2023Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes
6012. ICLR 2023Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling
6013. ICLR 2023Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient
6014. ICLR 2023Offline RL for Natural Language Generation with Implicit Language Q Learning
6015. ICLR 2023Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization
6016. ICLR 2023On the Data-Efficiency with Contrastive Image Transformation in Reinforcement Learning
6017. ICLR 2023On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
6018. ICLR 2023On the Robustness of Safe Reinforcement Learning under Observational Perturbations
6019. ICLR 2023On the Sensitivity of Reward Inference to Misspecified Human Models
6020. ICLR 2023Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian
6021. ICLR 2023Optimal Transport for Offline Imitation Learning
6022. ICLR 2023Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics
6023. ICLR 2023Order Matters: Agent-by-agent Policy Optimization
6024. ICLR 2023Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation
6025. ICLR 2023PAC Reinforcement Learning for Predictive State Representations
6026. ICLR 2023Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms
6027. ICLR 2023PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm
6028. ICLR 2023Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs
6029. ICLR 2023Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
6030. ICLR 2023Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning
6031. ICLR 2023Planning Goals for Exploration
6032. ICLR 2023Planning with Sequence Models through Iterative Energy Minimization
6033. ICLR 2023Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
6034. ICLR 2023Policy-Based Self-Competition for Planning Problems
6035. ICLR 2023POPGym: Benchmarking Partially Observable Reinforcement Learning
6036. ICLR 2023Population-size-Aware Policy Optimization for Mean-Field Games
6037. ICLR 2023Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
6038. ICLR 2023Preference Transformer: Modeling Human Preferences using Transformers for RL
6039. ICLR 2023Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning
6040. ICLR 2023Proactive Multi-Camera Collaboration for 3D Human Pose Estimation
6041. ICLR 2023Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks
6042. ICLR 2023Provably Efficient Lifelong Reinforcement Learning with Linear Representation
6043. ICLR 2023Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path
6044. ICLR 2023Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots
6045. ICLR 2023Quality-Similar Diversity via Population Based Reinforcement Learning
6046. ICLR 2023Quasi-optimal Reinforcement Learning with Continuous Actions
6047. ICLR 2023ReAct: Synergizing Reasoning and Acting in Language Models
6048. ICLR 2023Recursive Time Series Data Augmentation
6049. ICLR 2023Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences
6050. ICLR 2023Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay

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。