Advice Exchange in Heterogeneous Groups of Learning Agents: Experimental Results in the Pursuit Domain

Abstract

The question that is addressed in this work is: ”(How) can a heterogeneous group of learning-agents, involved in solving similar problems, cooperate, by exchanging information, in order to improve their performance?” The approach taken, entitled ”AdviceExchange”, consists on requesting advice from agents that show good performance on the given problem and using this knowledge either as a desired response for supervised training or to provide extra reinforcement to the agent about a given action. This is the first step of a technique that aims at providing added capabilities to learning-agents that are solving similar problems in parallel.

60 Figures and Tables

Cite this paper

@inproceedings{Nunes2002AdviceEI, title={Advice Exchange in Heterogeneous Groups of Learning Agents: Experimental Results in the Pursuit Domain}, author={Lu{\'i}s Nunes and Marcos Danillo P Oliveira}, year={2002} }