Techniques for batch reinforcement learning in robotics
This thesis addresses the Batch Reinforcement Learning methods in Robotics. This sub-class of Reinforcement Learning has shown promising results and has been the focus of recent research. Three contributions are proposed that aim to extend the state-of-art methods allowing for a faster and more stab...
| Autor principal: | |
|---|---|
| Formato: | doctoralThesis |
| Idioma: | eng |
| Publicado em: |
2016
|
| Assuntos: | |
| Texto completo: | http://hdl.handle.net/10773/15735 |
| País: | Portugal |
| Oai: | oai:ria.ua.pt:10773/15735 |