This literature review aims to thoroughly examine the current landscape of Safe Reinforcement Learning techniques for autonomous vehicles. The paper aims to cover various topics around safe RL, including value function approximation, policy optimization, model-based reinforcement learning, safe exploration te...
A Safe Reinforcement Learning method is proposed for solving the problem. The objective is to minimize expected energy consumption in a safe way, which means also minimizing the risk of battery depletion while en route by planning charging whenever necessary. The key idea is to learn offline ...
这篇文章将为大家解析由慕尼黑工业大学、同济大学、加州大学伯克利分校、伦敦大学学院、伦敦国王大学和北京大学的研究人员联合发布的综述《安全强化学习:方法、理论与应用》的重要观点,深入探讨安全强化学习的研究现状、关键问题及未来发展方向。 论文标题:A Review of Safe Reinforcement Learning: Methods, Theories and Ap...
A review of off-policy evaluation in reinforcement learning. arXiv preprint arXiv:2212.06355; 2022. Jia Y, Burden J, Lawton T, Habli I. Safe reinforcement learning for sepsis treatment. In: 2020 IEEE International Conference on Healthcare Informatics (ICHI). IEEE; 2020. pp. 1–7. Tang S...
Brunke L, Greeff M, Hall A W, et al. Safe learning in robotics: From learning-based control to safe reinforcement learning[J]. Annual Review of Control, Robotics, and Autonomous Systems, 2022, 5(1): 411-444. 安全强...
Safe-Reinforcement-Learning-Baselines The repository is for Safe Reinforcement Learning (RL) research, in which we investigate various safe RL baselines and safe RL benchmarks, including single agent RL and multi-agent RL. If any authors do not want their paper to be listed here, please feel ...
基于上述介绍和问题讨论, 本文在最优控制意义下针对自主无人系统的避障控制问题展开研究, 基于StaF和BF提出一种安全自适应强化学习 (safe adaptive reinforcement learning, SARL) 方法, 通过状态外推和经验回放实现对障碍物的有效规避. 主要贡献在于: (1) 结合障碍函数, 设计了一种新颖的奖惩函数, 从而将避障问题...
A Review of Safe Reinforcement Learning: Methods, Theories, and Applications 2024, IEEE Transactions on Pattern Analysis and Machine Intelligence Multi-UAV Path Planning and Following Based on Multi-Agent Reinforcement Learning 2024, Drones View all citing articles on Scopus☆...
Researchers have explored using Deep Reinforcement Learning (DRL) to improve platooning performance. DRL is a subfield of machine learning that uses Deep Neural Networks (DNN) to approximate intricate values or policy functions, enabling more sophisticated and adaptable decision-making in dynamic and un...
Paper tables with annotated results for Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving