Autonomous Subgoal Discovery and Hierarchical Abstraction for Reinforcement Learning Using Monte Carlo Method
Abstract
Autonomous systems are often difficult to program. Reinforcement learning (RL) is an attractive alternative, as it allows the agent to learn behavior on the basis of sparse, delayed reward signals provided only when the agent reaches desired goals. However, standard reinforcement learning methods do not scale well for larger, more complex tasks. One promising approach to scaling up RL is hierarchical reinforcement learning
Cite
Text
Asadi and Huber. "Autonomous Subgoal Discovery and Hierarchical Abstraction for Reinforcement Learning Using Monte Carlo Method." AAAI Conference on Artificial Intelligence, 2005.Markdown
[Asadi and Huber. "Autonomous Subgoal Discovery and Hierarchical Abstraction for Reinforcement Learning Using Monte Carlo Method." AAAI Conference on Artificial Intelligence, 2005.](https://mlanthology.org/aaai/2005/asadi2005aaai-autonomous/)BibTeX
@inproceedings{asadi2005aaai-autonomous,
title = {{Autonomous Subgoal Discovery and Hierarchical Abstraction for Reinforcement Learning Using Monte Carlo Method}},
author = {Asadi, Mehran and Huber, Manfred},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2005},
pages = {1588-1589},
url = {https://mlanthology.org/aaai/2005/asadi2005aaai-autonomous/}
}