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 6,885 篇，第 138 / 138 页

6851. NeurIPS 2023Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics
6852. NeurIPS 2023Towards robust and generalizable representations of extracellular data using contrastive learning
6853. NeurIPS 2023TradeMaster: A Holistic Quantitative Trading Platform Empowered by Reinforcement Learning
6854. NeurIPS 2023Train Hard, Fight Easy: Robust Meta Reinforcement Learning
6855. NeurIPS 2023Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning
6856. NeurIPS 2023Training Transitive and Commutative Multimodal Transformers with LoReTTa
6857. NeurIPS 2023Transportability for Bandits with Data from Different Environments
6858. NeurIPS 2023Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach
6859. NeurIPS 2023Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints
6860. NeurIPS 2023Two Heads are Better Than One: A Simple Exploration Framework for Efficient Multi-Agent Reinforcement Learning
6861. NeurIPS 2023Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization
6862. NeurIPS 2023Uncertainty-Aware Instance Reweighting for Off-Policy Learning
6863. NeurIPS 2023Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning
6864. NeurIPS 2023Understanding Contrastive Learning via Distributionally Robust Optimization
6865. NeurIPS 2023Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL
6866. NeurIPS 2023Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective
6867. NeurIPS 2023Unsupervised Behavior Extraction via Random Intent Priors
6868. NeurIPS 2023Unsupervised Learning for Solving the Travelling Salesman Problem
6869. NeurIPS 2023Use perturbations when learning from explanations
6870. NeurIPS 2023Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies
6871. NeurIPS 2023Video Prediction Models as Rewards for Reinforcement Learning
6872. NeurIPS 2023VOCE: Variational Optimization with Conservative Estimation for Offline Safe Reinforcement Learning
6873. NeurIPS 2023VTaC: A Benchmark Dataset of Ventricular Tachycardia Alarms from ICU Monitors
6874. NeurIPS 2023Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies
6875. NeurIPS 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research
6876. NeurIPS 2023Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets
6877. NeurIPS 2023WCLD: Curated Large Dataset of Criminal Cases from Wisconsin Circuit Courts
6878. NeurIPS 2023Weakly Coupled Deep Q-Networks
6879. NeurIPS 2023Weitzman's Rule for Pandora's Box with Correlations
6880. NeurIPS 2023When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning
6881. NeurIPS 2023When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
6882. NeurIPS 2023When is Agnostic Reinforcement Learning Statistically Tractable?
6883. NeurIPS 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
6884. NeurIPS 2023Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization
6885. NeurIPS 2023Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis

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。