期刊
NEURAL NETWORKS
卷 16, 期 7, 页码 985-994出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/S0893-6080(02)00235-6
关键词
reinforcement learning; hierarchical/modular architecture; MOSAIC non-linear control task; inter-module credit assignment; modular reward
Critical issues in modular or hierarchical reinforcement learning (RL) are (i) how to decompose a task into sub-tasks, (ii) how to achieve independence of learning of sub-tasks, and (iii) how to assure optimality of the composite policy for the entire task. The second and last requirements are often under trade-off. We propose a method for propagating the reward for the entire task achievement between modules. This is done in the form of a 'modular reward', which is calculated from the temporal difference of the module gating signal and the value of the succeeding module. We implement modular reward for a multiple model-based reinforcement learning (MMRL) architecture and show its effectiveness in simulations of a pursuit task with hidden states and a continuous-time non-linear control task. (C) 2003 Elsevier Science 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