Automatic State Abstraction from Demonstration
Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 1243-1247.
Abstract
Learning from Demonstration (LfD) is a popular technique for building decision-making agents from human help. Traditional LfD methods use demonstrations as training examples for supervised learning, but complex tasks can require more examples than is practical to obtain. We present Abstraction from Demonstration (AfD), a novel form of LfD that uses demonstrations to infer state abstractions and reinforcement learning (RL) methods in those abstract state spaces to build a policy. Empirical results show that AfD is greater than an order of magnitude more sample efficient than jus tusing demonstrations as training examples, and exponentially faster than RL alone.
@inproceedings{ijcai2011p211,
title = {Automatic State Abstraction from Demonstration},
author = {Cobo, Luis C. and Zang, Peng and Jr., Charles Lee Isbell and Thomaz, Andrea Lockerd},
booktitle = {Proceedings of the Twenty-Second International Joint Conference on
Artificial Intelligence, {IJCAI-11}},
publisher = {AAAI Press/International Joint Conferences on Artificial Intelligence},
editor = {Toby Walsh},
pages = {1243--1247},
year = {2011},
month = {7},
doi = {10.5591/978-1-57735-516-8/IJCAI11-211},
url = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-211},
}
TY - CPAPER TI - Automatic State Abstraction from Demonstration AU - Cobo, Luis C. AU - Zang, Peng AU - Jr., Charles Lee Isbell AU - Thomaz, Andrea Lockerd T2 - Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11 PB - AAAI Press/International Joint Conferences on Artificial Intelligence PY - 2011 SP - 1243 EP - 1247 DO - 10.5591/978-1-57735-516-8/IJCAI11-211 UR - https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-211 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
