Hierarchically Optimal Average Reward Reinforcement Learning
Full Text: icml02.psTwo notions of optimality have been explored in previous work on hierarchical reinforcement learning (HRL): hierarchical optimality, or the optimal policy in the space de ned by a task hierarchy, and a weaker local model called recursive optimality. In this paper, we introduce two new average-reward HRL algorithms for nding hierarchically optimal policies.
Citation
M. Ghavamzadeh, S. Mahadevan. "Hierarchically Optimal Average Reward Reinforcement Learning". International Conference on Machine Learning (ICML), Sydney Australia, pp 195-202, July 2002.Keywords: | |
Category: | In Conference |
BibTeX
@incollection{Ghavamzadeh+Mahadevan:ICML02, author = {Mohammad Ghavamzadeh and Sridhar Mahadevan}, title = {Hierarchically Optimal Average Reward Reinforcement Learning}, Pages = {195-202}, booktitle = {International Conference on Machine Learning (ICML)}, year = 2002, }Last Updated: June 11, 2007
Submitted by Staurt H. Johnson