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 11 / 22 页

501. ICML 2023Quantile Credit Assignment
502. ICML 2023Quantum Policy Gradient Algorithm with Optimized Action Decoding
503. ICML 2023RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution
504. ICML 2023Reachability-Aware Laplacian Representation in Reinforcement Learning
505. ICML 2023Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents
506. ICML 2023Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
507. ICML 2023Reinforcement Learning Can Be More Efficient with Multiple Rewards
508. ICML 2023Reinforcement Learning from Passive Data via Latent Intentions
509. ICML 2023Reinforcement Learning in Low-rank MDPs with Density Features
510. ICML 2023Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
511. ICML 2023Reinforcement Learning with History Dependent Dynamic Contexts
512. ICML 2023ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
513. ICML 2023Reparameterized Policy Learning for Multimodal Trajectory Optimization
514. ICML 2023Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
515. ICML 2023Representation-Driven Reinforcement Learning
516. ICML 2023Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition
517. ICML 2023Retrosynthetic Planning with Dual Value Networks
518. ICML 2023Revisiting Bellman Errors for Offline Model Selection
519. ICML 2023Revisiting Domain Randomization via Relaxed State-Adversarial Policy Optimization
520. ICML 2023Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation
521. ICML 2023Reward-Mixing MDPs with Few Latent Contexts are Learnable
522. ICML 2023RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents
523. ICML 2023Robust Collaborative Learning with Linear Gradient Overhead
524. ICML 2023Robust Satisficing MDPs
525. ICML 2023Robust Situational Reinforcement Learning in Face of Context Disturbances
526. ICML 2023Robust Subtask Learning for Compositional Generalization
527. ICML 2023Robustly Learning a Single Neuron via Sharpness
528. ICML 2023Safe Offline Reinforcement Learning with Real-Time Budget Constraints
529. ICML 2023SAM operates far from home: eigenvalue regularization as a dynamical phenomenon
530. ICML 2023Sample Complexity Bounds for Learning High-dimensional Simplices in Noisy Regimes
531. ICML 2023Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation
532. ICML 2023Scalable Safe Policy Improvement via Monte Carlo Tree Search
533. ICML 2023Scaling Laws for Reward Model Overoptimization
534. ICML 2023Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning
535. ICML 2023SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models
536. ICML 2023Semi-Offline Reinforcement Learning for Optimized Text Generation
537. ICML 2023Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories
538. ICML 2023Semiparametrically Efficient Off-Policy Evaluation in Linear Markov Decision Processes
539. ICML 2023Set-membership Belief State-based Reinforcement Learning for POMDPs
540. ICML 2023Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments
541. ICML 2023Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search
542. ICML 2023Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning
543. ICML 2023Simplified Temporal Consistency Reinforcement Learning
544. ICML 2023SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning
545. ICML 2023Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning
546. ICML 2023STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning
547. ICML 2023Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
548. ICML 2023STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition
549. ICML 2023StriderNet: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes
550. ICML 2023Subequivariant Graph Reinforcement Learning in 3D Environments

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。