Learning Factored Markov Decision Processes with Unawareness
Abstract
Methods for learning and planning in sequential decision problems often assume the learner is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we give a method to learn factored markov decision problems from both domain exploration and expert assistance, which guarantees convergence to near-optimal behaviour, even when the agent begins unaware of factors critical to success. Our experiments show our agent learns optimal behaviour on both small and large problems, and that conserving information on discovering new possibilities results in faster convergence.
Cite
Text
Innes and Lascarides. "Learning Factored Markov Decision Processes with Unawareness." Uncertainty in Artificial Intelligence, 2019.Markdown
[Innes and Lascarides. "Learning Factored Markov Decision Processes with Unawareness." Uncertainty in Artificial Intelligence, 2019.](https://mlanthology.org/uai/2019/innes2019uai-learning/)BibTeX
@inproceedings{innes2019uai-learning,
title = {{Learning Factored Markov Decision Processes with Unawareness}},
author = {Innes, Craig and Lascarides, Alex},
booktitle = {Uncertainty in Artificial Intelligence},
year = {2019},
pages = {123-133},
volume = {115},
url = {https://mlanthology.org/uai/2019/innes2019uai-learning/}
}