Planning with Closed-Loop Macro Actions
- Doina Precup, McGill University, Montreal
- Richard S. Sutton, Department of Computing Science, University of Alberta
- Satinder Singh, University of Michigan, Ann Arbor, MI
Planning and learning at multiple levels of temporal abstraction is a key problem for artificial intelligence. In this paper we summarize an approach to this problem based on the mathematical framework of Markov decision processes and reinforcement learning. Conventional model-based reinforcement learning uses primitive actions that last one time step and that can be modeled independently of the learning agent. These can be generalized to macro actions, multi-step actions specified by an
Citation
D. Precup, R. Sutton, S. Singh. "Planning with Closed-Loop Macro Actions". National Conference on Artificial Intelligence (AAAI), Providence, Rhode Island, pp 73-76, May 1997.| Keywords: | |
| Category: | In Conference |
BibTeX
@incollection{Precup+al:AAAI97,
author = {Doina Precup and Richard S. Sutton and Satinder Singh},
title = {Planning with Closed-Loop Macro Actions},
Pages = {73-76},
booktitle = {National Conference on Artificial Intelligence (AAAI)},
year = 1997,
}Last Updated: May 31, 2007Submitted by Staurt H. Johnson
