{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/75631"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/75631","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Bayesian nonparametric approaches for reinforcement learning in partially observable domains","abstract":"Making intelligent decisions from incomplete information is critical in many applications: for example, medical decisions must often be made based on a few vital signs, without full knowledge of a patient's condition, and speech-based interfaces must infer a user's needs from noisy microphone inputs. What makes these tasks hard is that we do not even have a natural representation with which to model the task; we must learn about the task's properties while simultaneously performing the task. Learning a representation for a task also involves a trade-off between modeling the data that we have seen previously and being able to make predictions about new data streams. In this thesis, we explore one approach for learning representations of stochastic systems using Bayesian nonparametric statistics. Bayesian nonparametric methods allow the sophistication of a representation to scale gracefully with the complexity in the data. We show how the representations learned using Bayesian nonparametric methods result in better performance and interesting learned structure in three contexts related to reinforcement learning in partially-observable domains: learning partially observable Markov Decision processes, taking advantage of expert demonstrations, and learning complex hidden structures such as dynamic Bayesian networks. In each of these contexts, Bayesian nonparametric approach provide advantages in prediction quality and often computation time.","abstract_html":"Making intelligent decisions from incomplete information is critical in many applications: for example, medical decisions must often be made based on a few vital signs, without full knowledge of a patient's condition, and speech-based interfaces must infer a user's needs from noisy microphone inputs. What makes these tasks hard is that we do not even have a natural representation with which to model the task; we must learn about the task's properties while simultaneously performing the task. Learning a representation for a task also involves a trade-off between modeling the data that we have seen previously and being able to make predictions about new data streams. In this thesis, we explore one approach for learning representations of stochastic systems using Bayesian nonparametric statistics. Bayesian nonparametric methods allow the sophistication of a representation to scale gracefully with the complexity in the data. We show how the representations learned using Bayesian nonparametric methods result in better performance and interesting learned structure in three contexts related to reinforcement learning in partially-observable domains: learning partially observable Markov Decision processes, taking advantage of expert demonstrations, and learning complex hidden structures such as dynamic Bayesian networks. In each of these contexts, Bayesian nonparametric approach provide advantages in prediction quality and often computation time.","abstract_has_math":false,"creators":["Doshi-Velez, Finale"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["Nicholas Roy."],"committee_chairs":[],"committee_members":[],"year":2012,"date_issued":"2012","date_published":"2012","updated_at":"2026-07-22T22:21:36Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/75631","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Nicholas Roy."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Doshi-Velez, Finale"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2012-12-13T18:47:37Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2012-12-13T18:47:37Z"]},{"key":"dc:date.issued","label":"Date","values":["2012"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/75631"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012.","Cataloged from PDF version of thesis.","Includes bibliographical references (p. 149-163)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Making intelligent decisions from incomplete information is critical in many applications: for example, medical decisions must often be made based on a few vital signs, without full knowledge of a patient's condition, and speech-based interfaces must infer a user's needs from noisy microphone inputs. What makes these tasks hard is that we do not even have a natural representation with which to model the task; we must learn about the task's properties while simultaneously performing the task. Learning a representation for a task also involves a trade-off between modeling the data that we have seen previously and being able to make predictions about new data streams. In this thesis, we explore one approach for learning representations of stochastic systems using Bayesian nonparametric statistics. Bayesian nonparametric methods allow the sophistication of a representation to scale gracefully with the complexity in the data. We show how the representations learned using Bayesian nonparametric methods result in better performance and interesting learned structure in three contexts related to reinforcement learning in partially-observable domains: learning partially observable Markov Decision processes, taking advantage of expert demonstrations, and learning complex hidden structures such as dynamic Bayesian networks. In each of these contexts, Bayesian nonparametric approach provide advantages in prediction quality and often computation time."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["Bayesian nonparametric approaches for reinforcement learning in partially observable domains"]}]}],"canonical_facts":{"dc:contributor.advisor":["Nicholas Roy."],"dc:contributor.department":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science."],"dc:creator":["Doshi-Velez, Finale"],"dc:date.accessioned":["2012-12-13T18:47:37Z"],"dc:date.available":["2012-12-13T18:47:37Z"],"dc:date.issued":["2012"],"dc:description":["Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012.","Cataloged from PDF version of thesis.","Includes bibliographical references (p. 149-163)."],"dc:description.abstract":["Making intelligent decisions from incomplete information is critical in many applications: for example, medical decisions must often be made based on a few vital signs, without full knowledge of a patient's condition, and speech-based interfaces must infer a user's needs from noisy microphone inputs. What makes these tasks hard is that we do not even have a natural representation with which to model the task; we must learn about the task's properties while simultaneously performing the task. Learning a representation for a task also involves a trade-off between modeling the data that we have seen previously and being able to make predictions about new data streams. In this thesis, we explore one approach for learning representations of stochastic systems using Bayesian nonparametric statistics. Bayesian nonparametric methods allow the sophistication of a representation to scale gracefully with the complexity in the data. We show how the representations learned using Bayesian nonparametric methods result in better performance and interesting learned structure in three contexts related to reinforcement learning in partially-observable domains: learning partially observable Markov Decision processes, taking advantage of expert demonstrations, and learning complex hidden structures such as dynamic Bayesian networks. In each of these contexts, Bayesian nonparametric approach provide advantages in prediction quality and often computation time."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/75631"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Bayesian nonparametric approaches for reinforcement learning in partially observable domains"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:21:36Z"}