A multi-agent reinforcement learning approach for the efficient control of mobile robot

This paper presents an application of the multi-agent reinforcement learning approach for the efficient control of a mobile robot. This approach is based on a multi-agent system applied to multi-wheel control. The robot´s platform is decomposed into driving modules agents that are trained independently. The proposed approach incorporates multiple Q-learning agents, which permits them to effectively control every wheel relative to other wheels. The power reward policy with common error reward is adjusted to produce efficient control. The proposed approach is applied for the distributed control of a multi-wheel platform, in order to provide energy consumption optimization.