Honda Motor Co., Ltd.
CONTROL APPARATUS, CONTROL METHOD FOR CONTROL APPARATUS, NON-TRANSITORY COMPUTER READABLE STORAGE MEDIUM, INFORMATION PROCESSING SERVER, INFORMATION PROCESSING METHOD, AND CONTROL SYSTEM FOR CONTROLLING SYSTEM USING REINFORCEMENT LEARNING

Abstract:

A control apparatus for performing predetermined control for a predetermined system using reinforcement learning detects an event in a life cycle of the predetermined system and, in response to the detection of the event, set an exploration parameter specified in accordance with the detected event as a value for adjusting a ratio of exploration in the reinforcement learning. The control apparatus executes the predetermined control using the reinforcement learning in accordance with the set exploration parameter. When a first event is detected, the control apparatus sets the exploration parameter so that makes the ratio of the exploration set during a first period after the first event is smaller than the ratio of the exploration set during a second period before the first event is detected.