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 21 / 24 页

1001. NeurIPS 2024Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation
1002. NeurIPS 2024Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
1003. NeurIPS 2024Normalization and effective learning rates in reinforcement learning
1004. NeurIPS 2024OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
1005. NeurIPS 2024Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
1006. NeurIPS 2024ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
1007. NeurIPS 2024Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
1008. NeurIPS 2024Off-policy estimation with adaptively collected data: the power of online learning
1009. NeurIPS 2024Off-Policy Selection for Initiating Human-Centric Experimental Design
1010. NeurIPS 2024Offline Behavior Distillation
1011. NeurIPS 2024Offline Multitask Representation Learning for Reinforcement Learning
1012. NeurIPS 2024Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
1013. NeurIPS 2024Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
1014. NeurIPS 2024OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
1015. NeurIPS 2024On the Complexity of Teaching a Family of Linear Behavior Cloning Learners
1016. NeurIPS 2024On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
1017. NeurIPS 2024On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games
1018. NeurIPS 2024One-Shot Safety Alignment for Large Language Models via Optimal Dualization
1019. NeurIPS 2024Online Control with Adversarial Disturbance for Continuous-time Linear Systems
1020. NeurIPS 2024Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
1021. NeurIPS 2024OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
1022. NeurIPS 2024Operator World Models for Reinforcement Learning
1023. NeurIPS 2024Opponent Modeling based on Subgoal Inference
1024. NeurIPS 2024Opponent Modeling with In-context Search
1025. NeurIPS 2024OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations
1026. NeurIPS 2024Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
1027. NeurIPS 2024Optimization-based Causal Estimation from Heterogeneous Environments
1028. NeurIPS 2024Optimizing Automatic Differentiation with Deep Reinforcement Learning
1029. NeurIPS 2024Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition
1030. NeurIPS 2024Oracle-Efficient Reinforcement Learning for Max Value Ensembles
1031. NeurIPS 2024Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
1032. NeurIPS 2024Parallelizing Model-based Reinforcement Learning Over the Sequence Length
1033. NeurIPS 2024Parseval Regularization for Continual Reinforcement Learning
1034. NeurIPS 2024Paths to Equilibrium in Games
1035. NeurIPS 2024PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
1036. NeurIPS 2024Periodic agent-state based Q-learning for POMDPs
1037. NeurIPS 2024Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
1038. NeurIPS 2024Pessimistic Backward Policy for GFlowNets
1039. NeurIPS 2024Policy Aggregation
1040. NeurIPS 2024Policy Learning from Tutorial Books via Understanding, Rehearsing and Introspecting
1041. NeurIPS 2024Policy Mirror Descent with Lookahead
1042. NeurIPS 2024Policy Optimization for Robust Average Reward MDPs
1043. NeurIPS 2024Policy-shaped prediction: avoiding distractions in model-based reinforcement learning
1044. NeurIPS 2024Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation
1045. NeurIPS 2024Predicting Future Actions of Reinforcement Learning Agents
1046. NeurIPS 2024Preference Alignment with Flow Matching
1047. NeurIPS 2024PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
1048. NeurIPS 2024Provable Partially Observable Reinforcement Learning with Privileged Information
1049. NeurIPS 2024Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation
1050. NeurIPS 2024Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation

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。