Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement Learning Settings with Applications to Negative Transfer
Abstract
Policy advice is a transfer learning method where a student agent is able to learn faster via advice from a teacher. However, both this and other reinforcement learning transfer methods have little theoretical analysis. This paper formally defines a setting where multiple teacher agents can provide advice to a student and introduces an algorithm to leverage both autonomous exploration and teacher's advice. Our regret bounds justify the intuition that good teachers help while bad teachers hurt. Using our formalization, we are also able to quantify, for the first time, when negative transfer can occur within such a reinforcement learning setting. PDF
Cite
Text
Zhan et al. "Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement Learning Settings with Applications to Negative Transfer." International Joint Conference on Artificial Intelligence, 2016.Markdown
[Zhan et al. "Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement Learning Settings with Applications to Negative Transfer." International Joint Conference on Artificial Intelligence, 2016.](https://mlanthology.org/ijcai/2016/zhan2016ijcai-theoretically/)BibTeX
@inproceedings{zhan2016ijcai-theoretically,
title = {{Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement Learning Settings with Applications to Negative Transfer}},
author = {Zhan, Yusen and Bou-Ammar, Haitham and Taylor, Matthew E.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2016},
pages = {2315-2321},
url = {https://mlanthology.org/ijcai/2016/zhan2016ijcai-theoretically/}
}