Accelerating Imitation Learning in Relational Domains via Transfer by Initialization
Abstract
The problem of learning to mimic a human expert/teacher 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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 28, 2013
- Accession Number
- AD1014298
Entities
People
- Kristian Kersting
- Phillip Odom
- Prasad Tadepalli
- Saket Joshi
- Sriraam Natarajan
- Tushar Khot
Organizations
- Indiana University