Reinforcement Learning
Reinforcement learning (RL) focuses on training agents to make optimal decisions in an environment by learning through trial and error, aiming to maximize cumulative rewards. Current research emphasizes improving RL's efficiency and robustness, particularly in areas like human-in-the-loop training (e.g., using human feedback to refine models), handling uncertainty and sparse rewards, and scaling to complex tasks (e.g., robotics, autonomous driving). Prominent approaches involve various policy gradient methods, Monte Carlo Tree Search, and the integration of large language models for improved decision-making and task decomposition. These advancements are driving progress in diverse fields, including robotics, game playing, and the development of more human-aligned AI systems.
Papers
Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning
Brett Barkley, David Fridovich-Keil
Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation
Benjamin Steenhoek, Michele Tufano, Neel Sundaresan, Alexey Svyatkovskiy
Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
Zhiyuan Zeng, Qinyuan Cheng, Zhangyue Yin, Bo Wang, Shimin Li, Yunhua Zhou, Qipeng Guo, Xuanjing Huang, Xipeng Qiu
Harvesting energy from turbulent winds with Reinforcement Learning
Lorenzo Basile, Maria Grazia Berni, Antonio Celani
Bayesian Critique-Tune-Based Reinforcement Learning with Attention-Based Adaptive Pressure for Multi-Intersection Traffic Signal Control
Wenchang Duan, Zhenguo Gao. Jinguo Xian
Learning Quadrupedal Robot Locomotion for Narrow Pipe Inspection
Jing Guo, Ziwei Wang, Weibang Bai
Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution
Changxin Huang, Yanbin Chang, Junfan Lin, Junyang Liang, Runhao Zeng, Jianqiang Li
Learning Visuotactile Estimation and Control for Non-prehensile Manipulation under Occlusions
Juan Del Aguila Ferrandis, João Moura, Sethu Vijayakumar
Reservoir Computing for Fast, Simplified Reinforcement Learning on Memory Tasks
Kevin McKee
SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks
Mátyás Vincze, Laura Ferrarotti, Leonardo Lucio Custode, Bruno Lepri, Giovanni Iacca
Future Aspects in Human Action Recognition: Exploring Emerging Techniques and Ethical Influences
Antonios Gasteratos, Stavros N. Moutsis, Konstantinos A. Tsintotas, Yiannis Aloimonos
Design of Restricted Normalizing Flow towards Arbitrary Stochastic Policy with Computational Efficiency
Taisuke Kobayashi, Takumi Aotani
Coordinated Power Smoothing Control for Wind Storage Integrated System with Physics-informed Deep Reinforcement Learning
Shuyi Wang, Huan Zhao, Yuji Cao, Zibin Pan, Guolong Liu, Gaoqi Liang, Junhua Zhao
ParMod: A Parallel and Modular Framework for Learning Non-Markovian Tasks
Ruixuan Miao, Xu Lu, Cong Tian, Bin Yu, Zhenhua Duan
Neural-Network-Driven Reward Prediction as a Heuristic: Advancing Q-Learning for Mobile Robot Path Planning
Yiming Ji, Kaijie Yun, Yang Liu, Zongwu Xie, Hong Liu
Lagrangian Index Policy for Restless Bandits with Average Reward
Konstantin Avrachenkov, Vivek S. Borkar, Pratik Shah
An Advantage-based Optimization Method for Reinforcement Learning in Large Action Space
Hai Lin, Cheng Huang, Zhihong Chen