Automated discovery of options in reinforcement learning
AI planning benefits greatly from the use of temporally-extended or macro-actions. Macro-actions allow for faster and more efficient planning as well as the reuse of knowledge from previous solutions. In recent years, a significant amount of research has been devoted to incorporating macro-action...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en |
| Published: |
McGill University
2004
|
| Subjects: | |
| Online Access: | http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=80881 |