Accelerating Imitation Learning in Relational Domains via Transfer by Initialization

The problem of learning to mimic a human expertteacher from training trajectories is called imitation learning. To make the process of teaching easier in this setting, we propose to employ transfer learning where one learns on a source problem and transfers the knowledge to potentially more complex target problems. We consider multirelational environments such as real-time strategy games and use functional-gradient boosting to capture and transfer the models learned in these environments.