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 18 / 22 页

851. NeurIPS 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
852. NeurIPS 2023Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms
853. NeurIPS 2023Model-Free Active Exploration in Reinforcement Learning
854. NeurIPS 2023Model-free Posterior Sampling via Learning Rate Randomization
855. NeurIPS 2023Model-Free Reinforcement Learning with the Decision-Estimation Coefficient
856. NeurIPS 2023Monte Carlo Tree Search with Boltzmann Exploration
857. NeurIPS 2023MoVie: Visual Model-Based Policy Adaptation for View Generalization
858. NeurIPS 2023Multi-Agent First Order Constrained Optimization in Policy Space
859. NeurIPS 2023Multi-Agent Meta-Reinforcement Learning: Sharper Convergence Rates with Task Similarity
860. NeurIPS 2023Multi-Modal Inverse Constrained Reinforcement Learning from a Mixture of Demonstrations
861. NeurIPS 2023Multi-Objective Intrinsic Reward Learning for Conversational Recommender Systems
862. NeurIPS 2023Multi-Step Generalized Policy Improvement by Leveraging Approximate Models
863. NeurIPS 2023Mutual Information Regularized Offline Reinforcement Learning
864. NeurIPS 2023Mutual-Information Regularized Multi-Agent Policy Iteration
865. NeurIPS 2023Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation
866. NeurIPS 2023Natural Language Instruction-following with Task-related Language Development and Translation
867. NeurIPS 2023Nearly Tight Bounds For Differentially Private Multiway Cut
868. NeurIPS 2023Necessary and Sufficient Conditions for Optimal Decision Trees using Dynamic Programming
869. NeurIPS 2023NetHack is Hard to Hack
870. NeurIPS 2023Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning
871. NeurIPS 2023Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement
872. NeurIPS 2023No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions
873. NeurIPS 2023Noether Embedding: Efficient Learning of Temporal Regularities
874. NeurIPS 2023Non-Convex Bilevel Optimization with Time-Varying Objective Functions
875. NeurIPS 2023NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos
876. NeurIPS 2023ODE-based Recurrent Model-free Reinforcement Learning for POMDPs
877. NeurIPS 2023OFCOURSE: A Multi-Agent Reinforcement Learning Environment for Order Fulfillment
878. NeurIPS 2023Off-Policy Evaluation for Human Feedback
879. NeurIPS 2023Offline Imitation Learning with Variational Counterfactual Reasoning
880. NeurIPS 2023Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage
881. NeurIPS 2023Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization
882. NeurIPS 2023Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management
883. NeurIPS 2023Offline Reinforcement Learning with Differential Privacy
884. NeurIPS 2023Offline RL with Discrete Proxy Representations for Generalizability in POMDPs
885. NeurIPS 2023On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
886. NeurIPS 2023On Imitation in Mean-field Games
887. NeurIPS 2023On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling and Beyond
888. NeurIPS 2023On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration
889. NeurIPS 2023On the Importance of Exploration for Generalization in Reinforcement Learning
890. NeurIPS 2023On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
891. NeurIPS 2023One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning
892. NeurIPS 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling
893. NeurIPS 2023Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost
894. NeurIPS 2023Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations
895. NeurIPS 2023Online Nonstochastic Model-Free Reinforcement Learning
896. NeurIPS 2023Online RL in Linearly $q^\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore
897. NeurIPS 2023OpenAssistant Conversations - Democratizing Large Language Model Alignment
898. NeurIPS 2023Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes
899. NeurIPS 2023Optimal cross-learning for contextual bandits with unknown context distributions
900. NeurIPS 2023Optimal Exploration for Model-Based RL in Nonlinear Systems

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。