This paper proposes a novel adaptive guidance system developed using reinforcement meta-learning with a recurrent policy and value function approximator. The use of recurrent network layers allows the deployed policy to adapt real time to environmental forces acting on the agent. We compare the performance of the DR/DV guidance law, an RL agent with a non-recurrent policy, and an RL agent with a recurrent policy in four difficult tasks with unknown but highly variable dynamics. These tasks include a safe Mars landing with random engine failure and a landing on an asteroid with unknown environmental dynamics. We also demonstrate the ability of a recurrent policy to navigate using only Doppler radar altimeter returns, thus integrating guidance and navigation.
Where to go: Agent Guidance with Deep Reinforcement Learning in A City-Scale Online Ride-Hailing Service
Utah State University（犹他州立大学）
在线乘车服务已成为世界各地流行的交通系统。在本文中，我们研究了一个具有挑战性的问题，即如何在城市周围引导空置的出租车，以便在在线乘车服务中实现供需平衡。我们设计了一个新的奖励计划，考虑了在线乘车服务的多个性能指标。我们还提出了一种新的深度强化学习方法，名为Deep-Q-Network with Action Mask（AM-DQN），该方法屏蔽了各个位置的不必要动作，从而使智能体可以更快，更有效地学习。我们使用芝加哥的城市规模数据集进行了广泛的实验。几种流行的启发式和学习方法也被实现为比较的基线。实验结果表明，AM-DQN的平均故障率，平均等待时间的客户，平均空闲搜索时间的空闲出租车方面达到所有方法的最佳性能。
Learning to Guide: Guidance Law Based on Deep Meta-learning and Model Predictive Path Integral Control
School of Automation Science and Electrical Engineering, Beihang University（北京航空航天大学自动化科学与电气工程学院）；Navigation and Control Technology Research Institute of China North Industries Group Corporation（中国北方工业集团有限公司导航与控制技术研究院）
Guidance Design for Escape Flight Vehicle Using Evolution Strategy Enhanced Deep Reinforcement Learning
School of Aerospace Engineering, Tsinghua University（清华大学航天航空学院）；China Academy of Launch Vehicle Technology（中国运载火箭技术研究院）；School of Information and Communication Engineering, Beijing University of Posts and Telecommunications（北京邮电大学信息与通信工程学院）
Image AID via continuous-time reinforcement learning
Department of Industrial Engineering and Operations Research, Columbia University, New York, NY 10027, USA（工业工程与运筹学系，哥伦比亚大学，纽约，NY 10027，美国）；Department of Industrial Engineering and Operations Research & Data Science Institute, Columbia University, New York, NY 10027, USA（工业工程与运筹学系及数据科学研究所，哥伦比亚大学，纽约，NY 10027，美国）
