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 1,070 篇，第 19 / 22 页

901. NeurIPS 2023Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making
902. NeurIPS 2023Optimistic Active Exploration of Dynamical Systems
903. NeurIPS 2023Optimistic Exploration in Reinforcement Learning Using Symbolic Model Estimates
904. NeurIPS 2023Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL
905. NeurIPS 2023Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method
906. NeurIPS 2023Ordering-based Conditions for Global Convergence of Policy Gradient Methods
907. NeurIPS 2023PAC Learning Linear Thresholds from Label Proportions
908. NeurIPS 2023Parallel-mentoring for Offline Model-based Optimization
909. NeurIPS 2023Parameterizing Non-Parametric Meta-Reinforcement Learning Tasks via Subtask Decomposition
910. NeurIPS 2023Percentile Criterion Optimization in Offline Reinforcement Learning
911. NeurIPS 2023Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms
912. NeurIPS 2023Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning
913. NeurIPS 2023PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks
914. NeurIPS 2023Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion
915. NeurIPS 2023PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
916. NeurIPS 2023Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data
917. NeurIPS 2023Policy Gradient for Rectangular Robust Markov Decision Processes
918. NeurIPS 2023Policy Optimization for Continuous Reinforcement Learning
919. NeurIPS 2023Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control
920. NeurIPS 2023Policy Space Diversity for Non-Transitive Games
921. NeurIPS 2023Posterior Sampling for Competitive RL: Function Approximation and Partial Observation
922. NeurIPS 2023Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
923. NeurIPS 2023Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning
924. NeurIPS 2023Prediction and Control in Continual Reinforcement Learning
925. NeurIPS 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
926. NeurIPS 2023Prioritizing Samples in Reinforcement Learning with Reducible Loss
927. NeurIPS 2023Probabilistic Inference in Reinforcement Learning Done Right
928. NeurIPS 2023Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization
929. NeurIPS 2023Provably (More) Sample-Efficient Offline RL with Options
930. NeurIPS 2023Provably Efficient Algorithm for Nonstationary Low-Rank MDPs
931. NeurIPS 2023Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability
932. NeurIPS 2023Provably Efficient Offline Reinforcement Learning in Regular Decision Processes
933. NeurIPS 2023Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games
934. NeurIPS 2023Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards
935. NeurIPS 2023Provably Safe Reinforcement Learning with Step-wise Violation Constraints
936. NeurIPS 2023Recovering from Out-of-sample States via Inverse Dynamics in Offline Reinforcement Learning
937. NeurIPS 2023Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
938. NeurIPS 2023ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints
939. NeurIPS 2023Reduced Policy Optimization for Continuous Control with Hard Constraints
940. NeurIPS 2023Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor
941. NeurIPS 2023Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans
942. NeurIPS 2023Reflexion: language agents with verbal reinforcement learning
943. NeurIPS 2023Regret Minimization via Saddle Point Optimization
944. NeurIPS 2023Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time
945. NeurIPS 2023Regularity as Intrinsic Reward for Free Play
946. NeurIPS 2023Regularized Behavior Cloning for Blocking the Leakage of Past Action Information
947. NeurIPS 2023Reinforcement Learning with Fast and Forgetful Memory
948. NeurIPS 2023Reinforcement Learning with Simple Sequence Priors
949. NeurIPS 2023Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressions
950. NeurIPS 2023Reining Generalization in Offline Reinforcement Learning via Representation Distinction

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。