Concurrent Hierarchical Reinforcement Learning

Marthi, Bhaskara; Russell, Stuart J.; Latham, David; Guestrin, Carlos

Concurrent Hierarchical Reinforcement Learning

Bhaskara Marthi, Stuart J. Russell, David Latham, Carlos Guestrin

Download BibTeX Cite

Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 779-784.

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.

Bhaskara Marthi, Stuart J. Russell, David Latham, and Carlos Guestrin. 2005. Concurrent Hierarchical Reinforcement Learning. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05. IJCAI, 779–784. https://ijcai.org/proceedings/2005/205

@inproceedings{ijcai2005p205,
  title     = {Concurrent Hierarchical Reinforcement Learning},
  author    = {Marthi, Bhaskara and Russell, Stuart J. and Latham, David and Guestrin, Carlos},
  booktitle = {Proceedings of the Nineteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-05}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  pages     = {779--784},
  year      = {2005},
  url       = {https://ijcai.org/proceedings/2005/205},
}

TY  - CPAPER
TI  - Concurrent Hierarchical Reinforcement Learning
AU  - Marthi, Bhaskara
AU  - Russell, Stuart J.
AU  - Latham, David
AU  - Guestrin, Carlos
T2  - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2005
SP  - 779
EP  - 784
UR  - https://ijcai.org/proceedings/2005/205
ER  -