Sharing in teams of heterogeneous, collaborative learning agents

Abstract

This paper is focused on the effects of sharing knowledge and collaboration of multiple heterogeneous, intelligent agents (hardware or software) which work together to learn a task. As each agent employs a different machine learning technique, the system consists of multiple knowledge sources and their respective heterogeneous knowledge representations. Collaboration between agents involves sharing knowledge to both speed up team learning, as well as refine the team's overall performance and group behavior. Experiments have been performed that vary the team composition in terms of machine learning algorithms, learning strategies employed by the agents, and sharing frequency for a predator-prey cooperative pursuit task. For lifelong learning, heterogeneous learning teams were more successful than homogeneous learning counterparts. Interestingly, sharing increased the learning rate, but sharing with higher frequency showed diminishing results. Lastly, knowledge conflicts are reduced over time the more sharing takes place. These results support further investigation of the merits of heterogeneous learning. C 2008 Wiley Periodicals, Inc.

Collaborative Sharing-Tasks Learning for Early Childhood Education

“…Research by Gifford & Arvin (2009) has shown that collaborative learning through heterogeneous groups can accelerate learning, as well as improve student performance and the entire group behaviors. The provision of complex problems can improve learning efficiency for each group member (Kirschner, Fred & Paul, 2011).…”

Collaborative multi-agent rock facies classification from wireline well log data

“…The goal of evaluating these aspects through detailed team studies is to study whether teams are better than an individual, combining decisions from multiple learners is useful, and that heterogeneous learning algorithms leads to higher task performance/accuracy (Gifford and Agah, 2009). The following sections present experimental results and discuss general aspects of team learning and collaboration discovered as part of this research.…”

Adapting the Predator-Prey Game Theoretic Environment to Army Tactical Edge Scenarios with Computational Multiagent Systems

“…Many multiagent research efforts utilize the original discretized predator-prey pursuit environment shown in Figure 1, implementing a toroidal grid world and requiring the single prey to be blocked on all sides by four predators [7,21,22]. These studies tend to focus less on the structure of the environment and more on how specific sets of predator strategies impact cooperation and teamwork in homogenous and heterogeneous groups of predators.…”