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 2,494 篇，第 37 / 50 页

1801. NeurIPS 2024Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation
1802. NeurIPS 2024MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training
1803. NeurIPS 2024Multi-Agent Coordination via Multi-Level Communication
1804. NeurIPS 2024Multi-Agent Domain Calibration with a Handful of Offline Data
1805. NeurIPS 2024Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
1806. NeurIPS 2024Multi-Reward Best Policy Identification
1807. NeurIPS 2024Multi-turn Reinforcement Learning with Preference Human Feedback
1808. NeurIPS 2024Multimodal Large Language Models Make Text-to-Image Generative Models Align Better
1809. NeurIPS 2024Mutli-Armed Bandits with Network Interference
1810. NeurIPS 2024N-agent Ad Hoc Teamwork
1811. NeurIPS 2024Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
1812. NeurIPS 2024Near-Optimal Distributionally Robust Reinforcement Learning with General $L_p$ Norms
1813. NeurIPS 2024Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
1814. NeurIPS 2024NeoRL: Efficient Exploration for Nonepisodic RL
1815. NeurIPS 2024NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
1816. NeurIPS 2024Neural Combinatorial Optimization for Robust Routing Problem with Uncertain Travel Times
1817. NeurIPS 2024NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning
1818. NeurIPS 2024No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
1819. NeurIPS 2024No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO
1820. NeurIPS 2024Noise Contrastive Alignment of Language Models with Explicit Rewards
1821. NeurIPS 2024Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation
1822. NeurIPS 2024Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
1823. NeurIPS 2024Normalization and effective learning rates in reinforcement learning
1824. NeurIPS 2024OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
1825. NeurIPS 2024Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
1826. NeurIPS 2024ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
1827. NeurIPS 2024Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
1828. NeurIPS 2024Off-policy estimation with adaptively collected data: the power of online learning
1829. NeurIPS 2024Off-Policy Selection for Initiating Human-Centric Experimental Design
1830. NeurIPS 2024Offline Behavior Distillation
1831. NeurIPS 2024Offline Multitask Representation Learning for Reinforcement Learning
1832. NeurIPS 2024Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
1833. NeurIPS 2024Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
1834. NeurIPS 2024OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
1835. NeurIPS 2024On the Complexity of Teaching a Family of Linear Behavior Cloning Learners
1836. NeurIPS 2024On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
1837. NeurIPS 2024On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games
1838. NeurIPS 2024One-Shot Safety Alignment for Large Language Models via Optimal Dualization
1839. NeurIPS 2024Online Control with Adversarial Disturbance for Continuous-time Linear Systems
1840. NeurIPS 2024Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
1841. NeurIPS 2024OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
1842. NeurIPS 2024Operator World Models for Reinforcement Learning
1843. NeurIPS 2024Opponent Modeling based on Subgoal Inference
1844. NeurIPS 2024Opponent Modeling with In-context Search
1845. NeurIPS 2024OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations
1846. NeurIPS 2024Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
1847. NeurIPS 2024Optimization-based Causal Estimation from Heterogeneous Environments
1848. NeurIPS 2024Optimizing Automatic Differentiation with Deep Reinforcement Learning
1849. NeurIPS 2024Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition
1850. NeurIPS 2024Oracle-Efficient Reinforcement Learning for Max Value Ensembles

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。