Imitation Learning of Team-play in Multiagent System based on Hidden Markov Modeling

Itsuki Noda

Abstract: This paper addresses agents' intentions as building blocks of imitation learning that abstract local situations of the agent, and proposes a hierarchical hidden Markov model (HMM) to represent cooperative behaviors of teamworks. The key of the proposed model is introduction of gate probabilities that restrict transition among agents' intentions according to others' intentions. Using these probabilities, the framework can control transitions flexibly among basic behaviors in a cooperative behavior.