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...

Full description

Bibliographic Details
Main Author:	Salter, S
Other Authors:	Posner, I
Format:	Thesis
Language:	English
Published:	2022
Subjects:	Reinforcement learning Neural networks (Computer science) Machine learning Artificial intelligence Deep learning (Machine learning) Transfer learning (Machine learning) Skills Robotics Modularity and Composition Domain Adaptation Continual Learning Knowledge Abstractions

Discovering knowledge abstractions for sample efficient embodied transfer learning

Similar Items