通用机器学习 · reinforcement learning论文趋势 2023–2026

主要结论

• 通用机器学习 · reinforcement learning论文从 2023 年的 287 篇增长到 2026 年的 575 篇，三年间扩大到约 2.0 倍。
• ICLR 是发通用机器学习 · reinforcement learning论文最多的会议，2023–2026 年共 847 篇，占四个会议总量的 51%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 34 篇。
• 在「通用机器学习」的 6 个主题里，它的 2026 年论文数排第 2；同组增长最快的通用机器学习 · evaluation是 4.3 倍，通用机器学习 · reinforcement learning是 2.0 倍。

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 2026The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
• ICML 2026De-attribute to Forget for LLM Unlearning
• ICLR 2026AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking
• CVPR 2026Dynamic Important Example Mining for Reinforcement Finetuning
• NeurIPS 2025RULE: Reinforcement UnLEarning Achieves Forget-retain Pareto Optimality
• ICML 2025The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes
• ICLR 2025A General Framework for Off-Policy Learning with Partially-Observed Reward
• CVPR 2025Automated Proof of Polynomial Inequalities via Reinforcement Learning
• NeurIPS 2024Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
• ICML 2024Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation
• ICLR 2024Bandits with Replenishable Knapsacks: the Best of both Worlds
• CVPR 2024Improving Unsupervised Hierarchical Representation with Reinforcement Learning
• NeurIPS 2023General Munchausen Reinforcement Learning with Tsallis Kullback-Leibler Divergence
• ICML 2023Non-stationary Reinforcement Learning under General Function Approximation
• ICLR 2023A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning
• CVPR 2023Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning
• NeurIPS 2026Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
• ICML 2026Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
• ICLR 2026APPLE: Toward General Active Perception via Reinforcement Learning
• CVPR 2026Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition

全部通用机器学习 · reinforcement learning论文

共 411 篇，第 8 / 9 页

351. NeurIPS 2025Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning
352. NeurIPS 2025Learning Parameterized Skills from Demonstrations
353. NeurIPS 2025Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards
354. NeurIPS 2025Learning to Clean: Reinforcement Learning for Noisy Label Correction
355. NeurIPS 2025Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning
356. NeurIPS 2025Meta-learning how to Share Credit among Macro-Actions
357. NeurIPS 2025Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning
358. NeurIPS 2025Mixture-of-Experts Meets In-Context Reinforcement Learning
359. NeurIPS 2025Novel Exploration via Orthogonality
360. NeurIPS 2025Offline Actor-Critic for Average Reward MDPs
361. NeurIPS 2025Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations
362. NeurIPS 2025Offline imitation learning in $Q^\pi$-realizable MDPs without expert realizability
363. NeurIPS 2025Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
364. NeurIPS 2025On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
365. NeurIPS 2025On the Sample Complexity Bounds of Bilevel Reinforcement Learning
366. NeurIPS 2025Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
367. NeurIPS 2025Optimal Regret Bounds via Low-Rank Structured Variation in Non-Stationary Reinforcement Learning
368. NeurIPS 2025Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning
369. NeurIPS 2025Perception-R1: Pioneering Perception Policy with Reinforcement Learning
370. NeurIPS 2025Preference Distillation via Value based Reinforcement Learning
371. NeurIPS 2025Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
372. NeurIPS 2025Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning
373. NeurIPS 2025Progress Reward Model for Reinforcement Learning via Large Language Models
374. NeurIPS 2025Quantization-Free Autoregressive Action Transformer
375. NeurIPS 2025Real-World Reinforcement Learning of Active Perception Behaviors
376. NeurIPS 2025REINFORCE Converges to Optimal Policies with Any Learning Rate
377. NeurIPS 2025Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
378. NeurIPS 2025Reinforcement Learning with Backtracking Feedback
379. NeurIPS 2025Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach
380. NeurIPS 2025Reward-Aware Proto-Representations in Reinforcement Learning
381. NeurIPS 2025Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents
382. NeurIPS 2025Risk-Averse Total-Reward Reinforcement Learning
383. NeurIPS 2025RLVR-World: Training World Models with Reinforcement Learning
384. NeurIPS 2025RULE: Reinforcement UnLEarning Achieves Forget-retain Pareto Optimality
385. NeurIPS 2025Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
386. NeurIPS 2025SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data
387. NeurIPS 2025Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
388. NeurIPS 2025ShiQ: Bringing back Bellman to LLMs
389. NeurIPS 2025Skill-Driven Neurosymbolic State Abstractions
390. NeurIPS 2025Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics
391. NeurIPS 2025Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning
392. NeurIPS 2025Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning
393. NeurIPS 2025STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
394. NeurIPS 2025STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization
395. NeurIPS 2025State Entropy Regularization for Robust Reinforcement Learning
396. NeurIPS 2025Structured Reinforcement Learning for Combinatorial Decision-Making
397. NeurIPS 2025Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces
398. NeurIPS 2025The World Is Bigger: A Computationally-Embedded Perspective on the Big World Hypothesis
399. NeurIPS 2025Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning
400. NeurIPS 2025To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning

常见问题

2023–2026 年四大会议一共有多少篇通用机器学习 · reinforcement learning论文？

共 1,676 篇，按年份分别是 2023 年 287 篇、2024 年 403 篇、2025 年 411 篇、2026 年 575 篇。

NeurIPS 2026 有多少篇通用机器学习 · reinforcement learning论文？

NeurIPS 2026 有 113 篇通用机器学习 · reinforcement learning论文，上一届是 108 篇。

ICLR 2026 有多少篇通用机器学习 · reinforcement learning论文？

ICLR 2026 有 335 篇通用机器学习 · reinforcement learning论文，上一届是 230 篇。

ICML 2026 有多少篇通用机器学习 · reinforcement learning论文？

ICML 2026 有 113 篇通用机器学习 · reinforcement learning论文，上一届是 71 篇。

CVPR 2026 有多少篇通用机器学习 · reinforcement learning论文？

CVPR 2026 有 14 篇通用机器学习 · reinforcement learning论文，上一届是 2 篇。

哪个会议的通用机器学习 · reinforcement learning论文最多？

ICLR，2023–2026 年共 847 篇。