Sensor space discretization in autonomous agent based on entropy minimization of behavior outcomes

Abstract

Sensor space discretization is a significant issue for the realization of the autonomous agents which are expected to decide and learn the proper behavior with various kinds of sensor information. This paper proposes a new sensor space discretization method based on entropy minimization of the agent's behavior outcomes. This framework unifies a variety of heuristic discretization policies used in the previous works, and provides a more general insight into this problem. An experimental study is also presented in the latter part, which suggests that our sensor discretization method greatly increases the adaptability of the agents to the environment when combined with existing behavior learning methods such as Q-Learning.