Effective and Efficient Memory for Generally Intelligent Agents.
dc.contributor.author | Derbinsky, Nathaniel Leonard | en_US |
dc.date.accessioned | 2012-10-12T15:24:28Z | |
dc.date.available | NO_RESTRICTION | en_US |
dc.date.available | 2012-10-12T15:24:28Z | |
dc.date.issued | 2012 | en_US |
dc.date.submitted | 2012 | en_US |
dc.identifier.uri | https://hdl.handle.net/2027.42/93855 | |
dc.description.abstract | Intelligent systems with access to large stores of experience, or memory, can draw upon and reason about this knowledge in a variety of situations, such as to improve the efficacy of their learning, decision-making, and actions in the world. However, little research has examined the computational challenges that arise when real-time agents require access to large stores of knowledge over long periods of time. This dissertation explores the computational trade-offs involved in enhancing intelligent agents with effective and efficient memory. We exploit general properties of environments, tasks, and agent cues in order to develop scalable algorithms for episodic learning (autobiographical memory); semantic learning (context-independent store of facts and relations); and competence-preserving retention of learned knowledge (policies to forget memories while maintaining task performance). We evaluate these algorithms in Soar, a general cognitive architecture, for hours-to-days of real-time execution and demonstrate that agents with effective and efficient memory benefit along numerous dimensions when tasked within a variety of problem domains, including linguistics, planning, games, and mobile robotics. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | Artificial Intelligence | en_US |
dc.subject | Episodic Memory | en_US |
dc.subject | Semantic Memory | en_US |
dc.subject | Forgetting | en_US |
dc.subject | Soar | en_US |
dc.subject | Cognitive Architecture | en_US |
dc.title | Effective and Efficient Memory for Generally Intelligent Agents. | en_US |
dc.type | Thesis | en_US |
dc.description.thesisdegreename | PhD | en_US |
dc.description.thesisdegreediscipline | Computer Science and Engineering | en_US |
dc.description.thesisdegreegrantor | University of Michigan, Horace H. Rackham School of Graduate Studies | en_US |
dc.contributor.committeemember | Laird, John E. | en_US |
dc.contributor.committeemember | Lewis, Richard L. | en_US |
dc.contributor.committeemember | Cafarella, Michael John | en_US |
dc.contributor.committeemember | Kuipers, Benjamin | en_US |
dc.contributor.committeemember | Van Lent, Michael C. | en_US |
dc.subject.hlbsecondlevel | Computer Science | en_US |
dc.subject.hlbtoplevel | Engineering | en_US |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/93855/1/nlderbin_1.pdf | |
dc.owningcollname | Dissertations and Theses (Ph.D. and Master's) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.