Learning Factored Markov Decision Processes with Unawareness
Artificial Intelligence
2019-02-28 v1
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 small and large problems, and that conserving information on discovering new possibilities results in faster convergence.
Cite
@article{arxiv.1902.10619,
title = {Learning Factored Markov Decision Processes with Unawareness},
author = {Craig Innes and Alex Lascarides},
journal= {arXiv preprint arXiv:1902.10619},
year = {2019}
}