An Experts Algorithm for Transfer Learning
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 1065-1069.
Abstract
A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for its current task. There may, however, be multiple reasonable policies suggested by prior experience, and the agent must choose between them potentially without any a priori knowledge about their applicability to its current situation. We present an experts algorithm for efficiently choosing amongst candidate policies in solving an unknown Markov decision process task. We conclude with the results of experiments on two domains in which we generate candidate policies from solutions to related tasks and use our experts algorithm to choose amongst them.
@inproceedings{ijcai2007p172,
title = {An Experts Algorithm for Transfer Learning},
author = {Talvitie, Erik and Singh, Satinder},
booktitle = {Proceedings of the Twentieth International Joint Conference on
Artificial Intelligence, {IJCAI-07}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ramon López de Mántaras},
pages = {1065--1069},
year = {2007},
url = {https://ijcai.org/proceedings/2007/172},
}
TY - CPAPER TI - An Experts Algorithm for Transfer Learning AU - Talvitie, Erik AU - Singh, Satinder T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 SP - 1065 EP - 1069 UR - https://ijcai.org/proceedings/2007/172 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
