Building Adaptive Autonomous Agents for Adversarial Domains

Contents

This paper presents a methodology, called CAPTAIN, to build adaptive agents in an integrated framework that facilitates both building agents through knowledge elicitation and interactive apprenticeship learning from subject matter experts, and making these agents adapt and improve during their normal use through autonomous learning. Such an automated adaptive agent consists of an adversarial planner and a muitistrategy learner. CAPTAIN agents may function as substitutes for human participants in trainingoriented distributed interactive simulations.