| Título: | Automated discovery of options in reinforcement learning |
| Autores: | Stolle, Martin |
| Fecha: | 2004 |
| Publicador: | McGill University - MCGILL |
| Fuente: |
 |
| Tipo: | Electronic Thesis or Dissertation |
| Tema: |
Artificial Intelligence. Computer Science. |
| Descripción: | 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-actions in learned controllers, particularly in the context of Reinforcement Learning. One general approach is the use of options (temporally-extended actions) in Reinforcement Learning [22]. While the properties of options are well understood, it is not clear how to find new options automatically. In this thesis we propose two new algorithms for discovering options and compare them to one algorithm from the literature. We also contribute a new algorithm for learning with options which improves on the performance of two widely used learning algorithms. Extensive experiments are used to demonstrate the effectiveness of the proposed algorithms. |
| Idioma: | en |
1 Investigations on the form-genera Beauveria and Tritirachium por MacLeod, Donald Murdock | 6 Treatment and recovery in first-episode psychosis : a qualitative analysis of client experiences por Windell, Deborah L. |
2 Seismic sensitivity of tall guyed telecommunication towers. por Ghodrati Amiri, Gholamreza. | 7 |
3 Exploring the Relationship Between Assets and Family Stress Among Low-Income Families por Rothwell, David W.,Han, Chang-Keun | 8 |
4 The case for asset-based interventions with indigenous peoples: Evidence from Hawai‘i por Rothwell, David W. | 9 |
5 Second Thoughts: Who Almost Participates in an IDA Program? por Rothwell, David W.,Han, Chang-Keun | 10 Recent contributions to the phenomenology of musical time : a critical survey por Beaudreau, Pierre |