Online Markov Decision Processes

Eyal Even-Dar, Sham M. Kakade, Yishay MansourMath. Oper. Res 2009 · OpenReview

Abstract

We consider a Markov decision process (MDP) setting in which the reward function is allowed to change after each time step (possibly in an adversarial manner), yet the dynamics remain fixed. Simila...
BibTeX
@inproceedings{evendar2009online,
  author = {Eyal Even-Dar and Sham M. Kakade and Yishay Mansour},
  title = {{Online Markov Decision Processes}},
  booktitle = {Math. Oper. Res},
  year = {2009},
  url = {https://openreview.net/forum?id=Km-zgMMPTbP},
}

Loading related content...

Figure