Open Access. Powered by Scholars. Published by Universities.®
- Discipline
Articles 1 - 2 of 2
Full-Text Articles in Computer Sciences
The Development Of Hierarchical Knowledge In Robot Systems, Stephen W. Hart
The Development Of Hierarchical Knowledge In Robot Systems, Stephen W. Hart
Open Access Dissertations
This dissertation investigates two complementary ideas in the literature on machine learning and robotics--those of embodiment and intrinsic motivation--to address a unified framework for skill learning and knowledge acquisition. "Embodied" systems make use of structure derived directly from sensory and motor configurations for learning behavior. Intrinsically motivated systems learn by searching for native, hedonic value through interaction with the world. Psychological theories of intrinsic motivation suggest that there exist internal drives favoring open-ended cognitive development and exploration. I argue that intrinsically motivated, embodied systems can learn generalizable skills, acquire control knowledge, and form an epistemological understanding of the world …
Action-Based Representation Discovery In Markov Decision Processes, Sarah Osentoski
Action-Based Representation Discovery In Markov Decision Processes, Sarah Osentoski
Open Access Dissertations
This dissertation investigates the problem of representation discovery in discrete Markov decision processes, namely how agents can simultaneously learn representation and optimal control. Previous work on function approximation techniques for MDPs largely employed hand-engineered basis functions. In this dissertation, we explore approaches to automatically construct these basis functions and demonstrate that automatically constructed basis functions significantly outperform more traditional, hand-engineered approaches. We specifically examine two problems: how to automatically build representations for action-value functions by explicitly incorporating actions into a representation, and how representations can be automatically constructed by exploiting a pre-specified task hierarchy. We first introduce a technique for …