强化学习论文趋势 2023–2026
策略优化、离线 RL 与基于环境的决策学习
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 6,885 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 484 | 233 | 297 | 56 | 1,070 |
| 2024 | 466 | 304 | 356 | 64 | 1,190 |
| 2025 | 784 | 379 | 405 | 72 | 1,640 |
| 2026 | 760 | 911 | 1,021 | 293 | 2,985 |
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 1,190 篇，第 4 / 24 页
- ICLR 2024Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
- ICLR 2024Eureka: Human-Level Reward Design via Coding Large Language Models
- ICLR 2024Explaining Kernel Clustering via Decision Trees
- ICLR 2024Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
- ICLR 2024Exploring the Promise and Limits of Real-Time Recurrent Learning
- ICLR 2024Fast Hyperboloid Decision Tree Algorithms
- ICLR 2024Fast Imitation via Behavior Foundation Models
- ICLR 2024Fast Value Tracking for Deep Reinforcement Learning
- ICLR 2024Federated Q-Learning: Linear Regret Speedup with Low Communication Cost
- ICLR 2024Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
- ICLR 2024First-order ANIL provably learns representations despite overparametrisation
- ICLR 2024FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning
- ICLR 2024Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation
- ICLR 2024Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
- ICLR 2024Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
- ICLR 2024Goodhart's Law in Reinforcement Learning
- ICLR 2024GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
- ICLR 2024H-GAP: Humanoid Control with a Generalist Planner
- ICLR 2024Harnessing Density Ratios for Online Reinforcement Learning
- ICLR 2024HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments
- ICLR 2024Hindsight PRIORs for Reward Learning from Human Preferences
- ICLR 2024Horizon-Free Regret for Linear Markov Decision Processes
- ICLR 2024Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
- ICLR 2024Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response
- ICLR 2024Identifying Policy Gradient Subspaces
- ICLR 2024Illusory Attacks: Information-theoretic detectability matters in adversarial attacks
- ICLR 2024Imitation Learning from Observation with Automatic Discount Scheduling
- ICLR 2024Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control
- ICLR 2024Improved Efficiency Based on Learned Saccade and Continuous Scene Reconstruction From Foveated Visual Sampling
- ICLR 2024Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
- ICLR 2024Improving Intrinsic Exploration by Creating Stationary Objectives
- ICLR 2024Improving Offline RL by Blending Heuristics
- ICLR 2024In-context Exploration-Exploitation for Reinforcement Learning
- ICLR 2024Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
- ICLR 2024Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task Substructures
- ICLR 2024Intelligent Switching for Reset-Free RL
- ICLR 2024Interpretable Meta-Learning of Physical Systems
- ICLR 2024Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
- ICLR 2024Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies
- ICLR 2024L2P-MIP: Learning to Presolve for Mixed Integer Programming
- ICLR 2024Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
- ICLR 2024Language Model Detectors Are Easily Optimized Against
- ICLR 2024Language Model Self-improvement by Reinforcement Learning Contemplation
- ICLR 2024Large Language Models as Generalizable Policies for Embodied Tasks
- ICLR 2024Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior
- ICLR 2024Learning Energy Decompositions for Partial Inference in GFlowNets
- ICLR 2024Learning from Sparse Offline Datasets via Conservative Density Estimation
- ICLR 2024Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
- ICLR 2024Learning Interactive Real-World Simulators
- ICLR 2024Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查强化学习在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "reinforcement-learning"}
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。