Automated State Abstraction for Options using the U-Tree Algorithm

Anders Jonsson, Andrew G. Barto
2000 Neural Information Processing Systems  
Learning a complex task can be significantly facilitated by defining a hierarchy of subtasks. An agent can learn to choose between various temporally abstract actions, each solving an assigned subtask, to accomplish the overall task. In this paper, we study hierarchical learning using the framework of options. We argue that to take full advantage of hierarchical structure, one should perform option-specific state abstraction, and that if this is to scale to larger tasks, state abstraction
more » ... be automated. We adapt McCallum's U-Tree algorithm to automatically build option-specific representations of the state feature space, and we illustrate the resulting algorithm using a simple hierarchical task. Results suggest that automated option-specific state abstraction is an attractive approach to making hierarchical learning systems more effective.
dblp:conf/nips/JonssonB00 fatcat:vcostp3iezgephe2stknze3fva