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 17 / 22 页

801. NeurIPS 2023Iteratively Learn Diverse Strategies with State Distance Information
802. NeurIPS 2023Katakomba: Tools and Benchmarks for Data-Driven NetHack
803. NeurIPS 2023Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control
804. NeurIPS 2023Kernelized Reinforcement Learning with Order Optimal Regret Bounds
805. NeurIPS 2023Koopman Kernel Regression
806. NeurIPS 2023KuaiSim: A Comprehensive Simulator for Recommender Systems
807. NeurIPS 2023Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information
808. NeurIPS 2023Language Model Alignment with Elastic Reset
809. NeurIPS 2023Language Models can Solve Computer Tasks
810. NeurIPS 2023Large Language Models Are Semi-Parametric Reinforcement Learning Agents
811. NeurIPS 2023Large Language Models can Implement Policy Iteration
812. NeurIPS 2023Latent exploration for Reinforcement Learning
813. NeurIPS 2023Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback
814. NeurIPS 2023Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning
815. NeurIPS 2023Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning
816. NeurIPS 2023Learning Exponential Families from Truncated Samples
817. NeurIPS 2023Learning from Active Human Involvement through Proxy Value Propagation
818. NeurIPS 2023Learning from Visual Observation via Offline Pretrained State-to-Go Transformer
819. NeurIPS 2023Learning Generalizable Agents via Saliency-guided Features Decorrelation
820. NeurIPS 2023Learning Multi-agent Behaviors from Distributed and Streaming Demonstrations
821. NeurIPS 2023Learning non-Markovian Decision-Making from State-only Sequences
822. NeurIPS 2023Learning Regularized Monotone Graphon Mean-Field Games
823. NeurIPS 2023Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
824. NeurIPS 2023Learning Shared Safety Constraints from Multi-task Demonstrations
825. NeurIPS 2023Learning Space-Time Continuous Latent Neural PDEs from Partially Observed States
826. NeurIPS 2023Learning the Efficient Frontier
827. NeurIPS 2023Learning Time-Invariant Representations for Individual Neurons from Population Dynamics
828. NeurIPS 2023Learning to Discover Skills through Guidance
829. NeurIPS 2023Learning to Influence Human Behavior with Offline Reinforcement Learning
830. NeurIPS 2023Learning to Modulate pre-trained Models in RL
831. NeurIPS 2023Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt
832. NeurIPS 2023Learning Unseen Modality Interaction
833. NeurIPS 2023Learning World Models with Identifiable Factorization
834. NeurIPS 2023Lending Interaction Wings to Recommender Systems with Conversational Agents
835. NeurIPS 2023LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios
836. NeurIPS 2023Likelihood Ratio Confidence Sets for Sequential Decision Making
837. NeurIPS 2023LIMA: Less Is More for Alignment
838. NeurIPS 2023List and Certificate Complexities in Replicable Learning
839. NeurIPS 2023LogSpecT: Feasible Graph Learning Model from Stationary Signals with Recovery Guarantees
840. NeurIPS 2023Long-Term Fairness with Unknown Dynamics
841. NeurIPS 2023Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL
842. NeurIPS 2023Loss Dynamics of Temporal Difference Reinforcement Learning
843. NeurIPS 2023Macro Placement by Wire-Mask-Guided Black-Box Optimization
844. NeurIPS 2023MAG-GNN: Reinforcement Learning Boosted Graph Neural Network
845. NeurIPS 2023Making Scalable Meta Learning Practical
846. NeurIPS 2023Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off
847. NeurIPS 2023Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration
848. NeurIPS 2023Maximum State Entropy Exploration using Predecessor and Successor Representations
849. NeurIPS 2023MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning
850. NeurIPS 2023MIMEx: Intrinsic Rewards from Masked Input Modeling

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。