Concurrent Hierarchical Reinforcement Learning
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.
Cite
Text
Marthi et al. "Concurrent Hierarchical Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2005.Markdown
[Marthi et al. "Concurrent Hierarchical Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2005.](https://mlanthology.org/ijcai/2005/marthi2005ijcai-concurrent/)BibTeX
@inproceedings{marthi2005ijcai-concurrent,
title = {{Concurrent Hierarchical Reinforcement Learning}},
author = {Marthi, Bhaskara and Russell, Stuart and Latham, David and Guestrin, Carlos},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2005},
pages = {779-785},
url = {https://mlanthology.org/ijcai/2005/marthi2005ijcai-concurrent/}
}