Unknown mixing times in apprenticeship and reinforcement learning

Tom Zahavy; Alon Cohen; Haim Kaplan; Yishay Mansour

UAI 2020poster6 citations

Unknown mixing times in apprenticeship and reinforcement learning

Tom Zahavy, Alon Cohen, Haim Kaplan, Yishay Mansour

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.

BibTeX

@InProceedings{pmlr-v124-zahavy20a,
  title = 	 {Unknown mixing times in apprenticeship and reinforcement learning},
  author =       {Zahavy, Tom and Cohen, Alon and Kaplan, Haim and Mansour, Yishay},
  booktitle = 	 {Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI)},
  pages = 	 {430--439},
  year = 	 {2020},
  editor = 	 {Peters, Jonas and Sontag, David},
  volume = 	 {124},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {03--06 Aug},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v124/zahavy20a/zahavy20a.pdf},
  url = 	 {https://proceedings.mlr.press/v124/zahavy20a.html},
  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.}
}