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 48 / 50 页

2351. NeurIPS 2023Probabilistic Inference in Reinforcement Learning Done Right
2352. NeurIPS 2023Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization
2353. NeurIPS 2023Provably (More) Sample-Efficient Offline RL with Options
2354. NeurIPS 2023Provably Efficient Algorithm for Nonstationary Low-Rank MDPs
2355. NeurIPS 2023Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability
2356. NeurIPS 2023Provably Efficient Offline Reinforcement Learning in Regular Decision Processes
2357. NeurIPS 2023Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games
2358. NeurIPS 2023Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards
2359. NeurIPS 2023Provably Safe Reinforcement Learning with Step-wise Violation Constraints
2360. NeurIPS 2023Recovering from Out-of-sample States via Inverse Dynamics in Offline Reinforcement Learning
2361. NeurIPS 2023Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
2362. NeurIPS 2023ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints
2363. NeurIPS 2023Reduced Policy Optimization for Continuous Control with Hard Constraints
2364. NeurIPS 2023Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor
2365. NeurIPS 2023Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans
2366. NeurIPS 2023Reflexion: language agents with verbal reinforcement learning
2367. NeurIPS 2023Regret Minimization via Saddle Point Optimization
2368. NeurIPS 2023Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time
2369. NeurIPS 2023Regularity as Intrinsic Reward for Free Play
2370. NeurIPS 2023Regularized Behavior Cloning for Blocking the Leakage of Past Action Information
2371. NeurIPS 2023Reinforcement Learning with Fast and Forgetful Memory
2372. NeurIPS 2023Reinforcement Learning with Simple Sequence Priors
2373. NeurIPS 2023Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressions
2374. NeurIPS 2023Reining Generalization in Offline Reinforcement Learning via Representation Distinction
2375. NeurIPS 2023Replicability in Reinforcement Learning
2376. NeurIPS 2023Replicable Reinforcement Learning
2377. NeurIPS 2023RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability
2378. NeurIPS 2023Resetting the Optimizer in Deep RL: An Empirical Study
2379. NeurIPS 2023Residual Q-Learning: Offline and Online Policy Customization without Value
2380. NeurIPS 2023Revisiting Implicit Differentiation for Learning Problems in Optimal Control
2381. NeurIPS 2023Revisiting the Minimalist Approach to Offline Reinforcement Learning
2382. NeurIPS 2023Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery
2383. NeurIPS 2023Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks
2384. NeurIPS 2023Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning
2385. NeurIPS 2023Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement
2386. NeurIPS 2023Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
2387. NeurIPS 2023Rewiring Neurons in Non-Stationary Environments
2388. NeurIPS 2023Risk-Averse Active Sensing for Timely Outcome Prediction under Cost Pressure
2389. NeurIPS 2023Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning
2390. NeurIPS 2023RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization
2391. NeurIPS 2023RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing
2392. NeurIPS 2023RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization
2393. NeurIPS 2023RoboCLIP: One Demonstration is Enough to Learn Robot Policies
2394. NeurIPS 2023RoboHive: A Unified Framework for Robot Learning
2395. NeurIPS 2023Robust Knowledge Transfer in Tiered Reinforcement Learning
2396. NeurIPS 2023Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms
2397. NeurIPS 2023Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms
2398. NeurIPS 2023SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations
2399. NeurIPS 2023Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark
2400. NeurIPS 2023Safety Verification of Decision-Tree Policies in Continuous Time

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。