The Robotics Institute

Carnegie Mellon Robotics Institute

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

While the need for hierarchies within control systems is apparent, it is also clear to many researchers that such hierarchies should be learned. Learning both the structure and the component behaviors is a difficult task. The benefit of learning the hierarchical structures of behaviors is that the decomposition of the control structure into smaller transportable chunks allows previously learned knowledge to be applied to new but related tasks. Presented in this paper are improvements to Nested Q-learning (NQL) that allow more realistic learning of control hierarchies in reinforcement environments. Also presented is a simulation of a simple robot performing a series of related tasks that is used to compare both hierarchical and non-hierarchal learning techniques.

Notes

Associated Center(s) / Consortia: Space Robotics Initiative and Field Robotics Center

Associated Project(s): Mars Autonomy

Text Reference

Bruce Digney, "Learning Hierarchical Control Structure for Multiple Tasks and Changing Environments," Proceedings of the Fifth Conference on the Simulation of Adaptive Behavior: SAB 98, 1998.

BibTeX Reference

@inproceedings{Digney_1998_3150,
   author = "Bruce Digney",
   title = "Learning Hierarchical Control Structure for Multiple Tasks and Changing Environments",
   booktitle = "Proceedings of the Fifth Conference on the Simulation of Adaptive Behavior: SAB 98",
   year = "1998",
}

The Robotics Institute

Menu