首页>
外国专利>
REINFORCEMENT LEARNING SYSTEM SUPPORTING DELAY COMPENSATION AND REINFORCEMENT LEARNING METHOD THEREOF
REINFORCEMENT LEARNING SYSTEM SUPPORTING DELAY COMPENSATION AND REINFORCEMENT LEARNING METHOD THEREOF
展开▼
机译:支持延迟补偿的强化学习系统及其强化学习方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention relates to a reinforcement learning method for supporting delay compensation in a reinforcement learning system. The reinforcement learning method using a reinforcement learning agent of the present invention includes the steps of: receiving an immediate compensation value and a delay compensation value associated with the control action from the environmental system; generating a final compensation value corresponding to the control action by considering the received immediate compensation value and the delay compensation value together; and generating a transition tuple including the final reward value, and applying the generated transition tuple to the reinforcement learning agent to perform reinforcement learning. Since the delay compensation value measured by being delayed in the environmental system can be applied to the directly related control action, the performance and speed of the reinforcement learning system can be increased.;COPYRIGHT KIPO 2020
展开▼