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 14 / 22 页

651. NeurIPS 2023Closing the Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits
652. NeurIPS 2023Coherent Soft Imitation Learning
653. NeurIPS 2023Combinatorial Optimization with Policy Adaptation using Latent Space Search
654. NeurIPS 2023Combining Behaviors with the Successor Features Keyboard
655. NeurIPS 2023Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems
656. NeurIPS 2023Complexity of Derivative-Free Policy Optimization for Structured $\mathcal{H}_\infty$ Control
657. NeurIPS 2023Compositional Generalization from First Principles
658. NeurIPS 2023Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees
659. NeurIPS 2023Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games
660. NeurIPS 2023Conditional Mutual Information for Disentangled Representations in Reinforcement Learning
661. NeurIPS 2023Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model
662. NeurIPS 2023Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems
663. NeurIPS 2023Conservative Offline Policy Adaptation in Multi-Agent Games
664. NeurIPS 2023Conservative State Value Estimation for Offline Reinforcement Learning
665. NeurIPS 2023Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards
666. NeurIPS 2023Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning
667. NeurIPS 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
668. NeurIPS 2023Context Shift Reduction for Offline Meta-Reinforcement Learning
669. NeurIPS 2023Contextual Bandits and Imitation Learning with Preference-Based Active Queries
670. NeurIPS 2023Continual Learning for Instruction Following from Realtime Feedback
671. NeurIPS 2023Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning
672. NeurIPS 2023Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
673. NeurIPS 2023Convergence of Actor-Critic with Multi-Layer Neural Networks
674. NeurIPS 2023COOM: A Game Benchmark for Continual Reinforcement Learning
675. NeurIPS 2023CORL: Research-oriented Deep Offline Reinforcement Learning Library
676. NeurIPS 2023Corruption-Robust Offline Reinforcement Learning with General Function Approximation
677. NeurIPS 2023Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning
678. NeurIPS 2023Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
679. NeurIPS 2023CQM: Curriculum Reinforcement Learning with a Quantized World Model
680. NeurIPS 2023Creating Multi-Level Skill Hierarchies in Reinforcement Learning
681. NeurIPS 2023Cross-Domain Policy Adaptation via Value-Guided Data Filtering
682. NeurIPS 2023Cross-Episodic Curriculum for Transformer Agents
683. NeurIPS 2023CS-Isolate: Extracting Hard Confident Examples by Content and Style Isolation
684. NeurIPS 2023Data Quality in Imitation Learning
685. NeurIPS 2023Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances
686. NeurIPS 2023De novo Drug Design using Reinforcement Learning with Multiple GPT Agents
687. NeurIPS 2023Debiased and Denoised Entity Recognition from Distant Supervision
688. NeurIPS 2023Debiasing Conditional Stochastic Optimization
689. NeurIPS 2023Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models
690. NeurIPS 2023Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees
691. NeurIPS 2023Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning
692. NeurIPS 2023Deep Reinforcement Learning with Plasticity Injection
693. NeurIPS 2023DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization
694. NeurIPS 2023Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization
695. NeurIPS 2023DIFFER:Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning
696. NeurIPS 2023Diffused Task-Agnostic Milestone Planner
697. NeurIPS 2023Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
698. NeurIPS 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Model
699. NeurIPS 2023Direct Preference-based Policy Optimization without Reward Modeling
700. NeurIPS 2023Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms

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。