Select Lab Publications


Concurrent Hierarchical Reinforcement Learning (2005)

By: Bhaskara Marthi, David Latham, Stuart Russell, and Carlos Guestrin

Abstract: We consider applying hierarchical reinforcement learning techniques to problems in which an agent has several effectors to control simultaneously. We argue that the kind of prior knowledge one typically has about such problems is best expressed using a multithreaded partial program, and present concurrent ALisp, a language for specifying such partial programs. We describe algorithms for learning and acting with concurrent ALisp that can be efficient even when there are exponentially many joint choices at each decision point. Finally, we show results of applying these methods to a complex computer game domain.

Download Information
Bhaskara Marthi, David Latham, Stuart Russell, and Carlos Guestrin (2005). "Concurrent Hierarchical Reinforcement Learning." Nineteenth International Joint Conference on Artificial Intelligence (IJCAI). pdf            
BibTeX citation

@inproceedings{Marthi+al:ijcai2005hrl,
author = {Bhaskara Marthi and David Latham and Stuart Russell and Carlos Guestrin},
title = {Concurrent Hierarchical Reinforcement Learning},
booktitle = {Nineteenth International Joint Conference on Artificial Intelligence (IJCAI)},
year = {2005},
address = {Edinburgh},
month = {July},
wwwfilebase = {ijcai2005-marthi-latham-russell-guestrin},
wwwtopic = {Multiagents}
}



full list