Concurrent Individual And Social Learning In Robot Teams. (9th March 2015)

• Record Type: Journal Article
• Authors: Ng, Larry; Emami, M. Reza
• Is Part Of: Computational intelligence. Volume 32:Number 3(2016)
• Page Start: 420
• Page End: 438
• Publication Date: 2015-03-09
• Subjects: multiagent system -- robot team -- cooperative learning -- advice‐sharing -- reinforcement learning; Artificial intelligence -- Periodicals; Computational linguistics -- Periodicals; 006.3
• DOI: 10.1111/coin.12060
• Languages: English
• ISSNs: 0824-7935

Abstract

Abstract : This article discusses effective mechanisms that enable a group of robots to autonomously generate, adapt, and enhance team behaviors while improving their individual performance simultaneously. Two promising team learning concepts, namely, cooperative learning and advice‐sharing, are integrated to provide a platform that encompasses a comprehensive approach to team‐performance enhancement. These methods were examined in relation to the performance characteristics of standard single‐robot Q‐learning to ascertain whether they retain viable learning characteristics despite the integration of individual learning into team behaviors.