Unknown Mixing Times in Apprenticeship and Reinforcement Learning
Abstract
We derive and analyze learning algorithms for apprenticeship learning, policy evaluation and policy gradient for average reward criteria. Existing algorithms explicitly require an upper bound on the mixing time. In contrast, we build on ideas from Markov chain theory and derive sampling algorithms that do not require such an upper bound. For these algorithms, we provide theoretical bounds on their sample-complexity and running time.
Cite
Text
Zahavy et al. "Unknown Mixing Times in Apprenticeship and Reinforcement Learning." Uncertainty in Artificial Intelligence, 2020.Markdown
[Zahavy et al. "Unknown Mixing Times in Apprenticeship and Reinforcement Learning." Uncertainty in Artificial Intelligence, 2020.](https://mlanthology.org/uai/2020/zahavy2020uai-unknown/)BibTeX
@inproceedings{zahavy2020uai-unknown,
title = {{Unknown Mixing Times in Apprenticeship and Reinforcement Learning}},
author = {Zahavy, Tom and Cohen, Alon and Kaplan, Haim and Mansour, Yishay},
booktitle = {Uncertainty in Artificial Intelligence},
year = {2020},
pages = {430-439},
volume = {124},
url = {https://mlanthology.org/uai/2020/zahavy2020uai-unknown/}
}