An Interconnected Dynamical System composed of dynamics-based Reinforcement Learning agents in a distributed environment: A case study

摘要

This paper presents a case study of an Interconnected Dynamical System (IDS) composed of Intelligent Reinforcement Learning (RL) agents, and characterized by a Hybrid P2P/Master-Slave architecture. In particular, we propose and extent our previously proposed non-dynamics-based RL work to make it an IDS. Furthermore, we study how the addition of motion constrains, knowledge sharing between agents, and distributed computing affect the overall performance of the system. In addition, we introduce a new dynamics based reward mechanism for reinforcement learning agents.