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 32 / 50 页

1551. NeurIPS 2024A Structure-Aware Framework for Learning Device Placements on Computation Graphs
1552. NeurIPS 2024A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
1553. NeurIPS 2024A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning
1554. NeurIPS 2024A Tractable Inference Perspective of Offline RL
1555. NeurIPS 2024A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch
1556. NeurIPS 2024A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective
1557. NeurIPS 2024Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation
1558. NeurIPS 2024Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process
1559. NeurIPS 2024Achieving Constant Regret in Linear Markov Decision Processes
1560. NeurIPS 2024Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
1561. NeurIPS 2024Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
1562. NeurIPS 2024Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps
1563. NeurIPS 2024Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning
1564. NeurIPS 2024Adaptive Exploration for Data-Efficient General Value Function Evaluations
1565. NeurIPS 2024Adaptive Labeling for Efficient Out-of-distribution Model Evaluation
1566. NeurIPS 2024Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
1567. NeurIPS 2024AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection
1568. NeurIPS 2024AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
1569. NeurIPS 2024ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
1570. NeurIPS 2024Adversarial Environment Design via Regret-Guided Diffusion Models
1571. NeurIPS 2024Adversarially Robust Decision Transformer
1572. NeurIPS 2024Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning
1573. NeurIPS 2024AGILE: A Novel Reinforcement Learning Framework of LLM Agents
1574. NeurIPS 2024Aligner: Efficient Alignment by Learning to Correct
1575. NeurIPS 2024Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
1576. NeurIPS 2024Aligning Individual and Collective Objectives in Multi-Agent Cooperation
1577. NeurIPS 2024Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
1578. NeurIPS 2024Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
1579. NeurIPS 2024Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
1580. NeurIPS 2024AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers
1581. NeurIPS 2024Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
1582. NeurIPS 2024Amortized Active Causal Induction with Deep Reinforcement Learning
1583. NeurIPS 2024Amortizing intractable inference in diffusion models for vision, language, and control
1584. NeurIPS 2024An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning
1585. NeurIPS 2024An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations
1586. NeurIPS 2024An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning
1587. NeurIPS 2024Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning
1588. NeurIPS 2024Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
1589. NeurIPS 2024AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games
1590. NeurIPS 2024Automated Multi-level Preference for MLLMs
1591. NeurIPS 2024Autoregressive Policy Optimization for Constrained Allocation Tasks
1592. NeurIPS 2024Axioms for AI Alignment from Human Feedback
1593. NeurIPS 2024Balancing Context Length and Mixing Times for Reinforcement Learning at Scale
1594. NeurIPS 2024Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
1595. NeurIPS 2024BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning
1596. NeurIPS 2024Belief-State Query Policies for User-Aligned POMDPs
1597. NeurIPS 2024BenchMARL: Benchmarking Multi-Agent Reinforcement Learning
1598. NeurIPS 2024Beyond Optimism: Exploration With Partially Observable Rewards
1599. NeurIPS 2024Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators
1600. NeurIPS 2024Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency

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。