Modular reinforcement learning for the detection of second order correlation of multi-sensors
Hayato Nakama, Satoshi Yamada · International Conference on Modelling, Identification and Control · 2010
The modular reinforcement learning system, which is composed of some control modules and a selection module, was developed to apply to the task where several types of sensor information were necessary for the control. In this study, the modular reinforcement learning was applied to the task where the second order correlation of two different sensors must be discriminated. The target (goal) has the correct image and lamp, and other objects have one of them or another image. To discriminate between the target and other objects, the “AND” condition of light sensors and camera must be distinguished. Since the learning efficiency was low, the iterative learning and the initial learning were proposed. As a result, the appropriate module selections and action selections were trained by the modular reinforcement learning.