Discovering knowledge abstractions for sample efficient embodied transfer learning
This thesis concerns sample-efficient embodied machine learning. Machine learning success in sequential decision problems has been limited to domains with a narrow range of goals, requiring orders more experience than humans. Additionally, they lack the ability to generalise to new related goals. In...
| Auteur principal: | |
|---|---|
| Autres auteurs: | |
| Format: | Thèse |
| Langue: | English |
| Publié: |
2022
|
| Sujets: |