期刊
AUTOMATICA
卷 78, 期 -, 页码 144-152出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.automatica.2016.12.009
关键词
H-infinity control; Off-policy reinforcement learning; Optimal control
资金
- NSF [ECCS-1405173, IIS-1208623, ECCS-1101401, ECCS-1230040]
- ONR grant [N00014-13-1-0562, N000141410718]
In this paper, a model-free solution to the H-infinity control of linear discrete-time systems is presented. The proposed approach employs off-policy reinforcement learning (RL) to solve the game algebraic Riccati equation online using measured data along the system trajectories. Like existing model-free RL algorithms, no knowledge of the system dynamics is required. However, the proposed method has two main advantages. First, the disturbance input does not need to be adjusted in a specific manner. This makes it more practical as the disturbance cannot be specified in most real-world applications. Second, there is no bias as a result of adding a probing noise to the control input to maintain persistence of excitation (PE) condition. Consequently, the convergence of the proposed algorithm is not affected by probing noise. An example of the H-infinity control for an F-16 aircraft is given. It is seen that the convergence of the new off-policy RL algorithm is insensitive to probing noise. (C) 2016 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据