@article{vanseijen2013efficient,
author = {van Seijen, Harm and Whiteson, Shimon and Kester, L.J.H.M.},
title = {Efficient abstraction selection in reinforcement learning},
year = {2013},
month = {August},
abstract = {This article addresses reinforcement learning problems based on factored Markov decision processes (MDPs) in which the agent must choose among a set of candidate abstractions, each build up from a different combination of state components. We present and evaluate a new approach that can perform effective abstraction selection that is more resource-efficient and/or more general than existing approaches. The core of the approach is to make selection of an abstraction part of the learning agent's decision-making process by augmenting the agent's action space with internal actions that select the abstraction it uses. We prove that under certain conditions this approach results in a derived MDP whose solution yields both the optimal abstraction for the original MDP and the optimal policy under that abstraction. We examine our approach in three domains of increasing complexity: contextual bandit problems, episodic MDPs, and general MDPs with context-specific structure. © 2013 Wiley Periodicals, Inc.},
url = {http://approjects.co.za/?big=en-us/research/publication/efficient-abstraction-selection-reinforcement-learning/},
pages = {657-699},
journal = {Computational Intelligence},
volume = {30-Apr},
}