Advice-Exchange Between Evolutionary Algorithms and Reinforcement Learning Agents: Experiments in the Pursuit Domain

Abstract

This research aims at studying the e ects of exchanging information during the learning process in Multiagent Systems. The concept of advice-exchange, introduced in previous contributions, consists in enabling an agent to request extra feedback, in the form of episodic advice, from other agents that are solving similar problems. The work that was previously focused on the exchange of information between agents that were solving detached problems is now concerned with groups of learning-agents that share the same environment. This change added new di culties to the task. The experiments reported below were conducted to detect the causes and correct the shortcomings that emerged when moving from environments where agents worked in detached problems to those where agents are interacting in the same environment. New concepts, such as self con dence, trust and advisor preference are introduced in this text.