Imitation learning using graphical models

Imitation-based learning is a general mechanism for rapid acquisition of new behaviors in autonomous agents and robots. In this paper, we propose a new approach to learning by imitation based on parameter learning in probabilistic graphical models. Graphical models are used not only to model an agent's own dynamics but also the dynamics of an observed teacher. Parameter tying between the agent-teacher models ensures consistency and facilitates learning. Given only observations of the teacher's states, we use the expect at ion-maximization (EM) algorithm to learn both dynamics and policies within graphical models. We present results demonstrating that EM-based imitation learning outperforms pure exploration-based learning on a benchmark problem (the FlagWorld domain). We additionally show that the graphical model representation can be leveraged to incorporate domain knowledge (e.g., state space factoring) to achieve significant speed-up in learning.