{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/41435"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/41435","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"A Distributed Q-learning Classifier System for task decomposition in real robot learning problems","abstract":"A distributed reinforcement-learning system is designed and implemented on a mobile robot for the study of complex task decomposition in real robot learning environments. The Distributed Q-learning Classifier System (DQLCS) is evolved from the standard Learning Classifier System (LCS) proposed by J.H. Holland. Two of the limitations of the standard LCS are its monolithic nature and its complex apportionment of credit scheme, the bucket brigade algorithm (BBA). The DQLCS addresses both of these problems as well as the inherent difficulties faced by learning systems operating in real environments. We introduce Q-learning as the apportionment of credit component of the DQLCS, and we develop a distributed learning architecture to facilitate complex task decomposition. Based upon dynamic programming, the Q-learning update equation is derived and its advantages over the complex BBA are discussed. The distributed architecture is implemented to provide for faster learning by allowing the system to effectively decrease the size of the problem space it must explore. Holistic and monolithic shaping approaches are used to distribute reward among the learning modules of the DQLCS in a variety of real robot learning experiments. The results of these experiments support the DQLCS as a useful reinforcement learning paradigm and suggest future areas of study in distributed learning systems.","abstract_html":"A distributed reinforcement-learning system is designed and implemented on a mobile robot for the study of complex task decomposition in real robot learning environments. The Distributed Q-learning Classifier System (DQLCS) is evolved from the standard Learning Classifier System (LCS) proposed by J.H. Holland. Two of the limitations of the standard LCS are its monolithic nature and its complex apportionment of credit scheme, the bucket brigade algorithm (BBA). The DQLCS addresses both of these problems as well as the inherent difficulties faced by learning systems operating in real environments. We introduce Q-learning as the apportionment of credit component of the DQLCS, and we develop a distributed learning architecture to facilitate complex task decomposition. Based upon dynamic programming, the Q-learning update equation is derived and its advantages over the complex BBA are discussed. The distributed architecture is implemented to provide for faster learning by allowing the system to effectively decrease the size of the problem space it must explore. Holistic and monolithic shaping approaches are used to distribute reward among the learning modules of the DQLCS in a variety of real robot learning experiments. The results of these experiments support the DQLCS as a useful reinforcement learning paradigm and suggest future areas of study in distributed learning systems.","abstract_has_math":false,"creators":["Chapman, Kevin L."],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Electrical Engineering","degree_department":"Electrical Engineering","school":null,"contributors":[],"advisors":[],"committee_chairs":["Bay, John S."],"committee_members":["Abbott, A. Lynn","VanLandingham, Hugh F."],"year":1996,"date_issued":"1996-09-05","date_published":"1996-09-05","updated_at":"2026-07-22T22:19:26Z","subjects":["Q-learning","Learning Classifier Systems","artificial intelligence","mobile robots","task decomposition"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-03042009-041449"],"render_values":[{"text":"etd-03042009-041449","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10919/41435","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Bay, John S."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Abbott, A. Lynn","VanLandingham, Hugh F."]},{"key":"dc:contributor.department","label":"Department","values":["Electrical Engineering"]},{"key":"dc:creator","label":"Author","values":["Chapman, Kevin L."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2014-03-14T21:31:02Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2014-03-14T21:31:02Z","2009-03-04"]},{"key":"dc:date.issued","label":"Date","values":["1996-09-05"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.dcmitype","label":"Dc Type Dcmitype","values":["Text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Q-learning","Learning Classifier Systems","artificial intelligence","mobile robots","task decomposition"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-03042009-041449"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10919/41435"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["A distributed reinforcement-learning system is designed and implemented on a mobile robot for the study of complex task decomposition in real robot learning environments. The Distributed Q-learning Classifier System (DQLCS) is evolved from the standard Learning Classifier System (LCS) proposed by J.H. Holland. Two of the limitations of the standard LCS are its monolithic nature and its complex apportionment of credit scheme, the bucket brigade algorithm (BBA). The DQLCS addresses both of these problems as well as the inherent difficulties faced by learning systems operating in real environments. We introduce Q-learning as the apportionment of credit component of the DQLCS, and we develop a distributed learning architecture to facilitate complex task decomposition. Based upon dynamic programming, the Q-learning update equation is derived and its advantages over the complex BBA are discussed. The distributed architecture is implemented to provide for faster learning by allowing the system to effectively decrease the size of the problem space it must explore. Holistic and monolithic shaping approaches are used to distribute reward among the learning modules of the DQLCS in a variety of real robot learning experiments. The results of these experiments support the DQLCS as a useful reinforcement learning paradigm and suggest future areas of study in distributed learning systems."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["BTD"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["A Distributed Q-learning Classifier System for task decomposition in real robot learning problems"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Bay, John S."],"dc:contributor.committeemember":["Abbott, A. Lynn","VanLandingham, Hugh F."],"dc:contributor.department":["Electrical Engineering"],"dc:creator":["Chapman, Kevin L."],"dc:date.accessioned":["2014-03-14T21:31:02Z"],"dc:date.available":["2014-03-14T21:31:02Z","2009-03-04"],"dc:date.issued":["1996-09-05"],"dc:description.abstract":["A distributed reinforcement-learning system is designed and implemented on a mobile robot for the study of complex task decomposition in real robot learning environments. The Distributed Q-learning Classifier System (DQLCS) is evolved from the standard Learning Classifier System (LCS) proposed by J.H. Holland. Two of the limitations of the standard LCS are its monolithic nature and its complex apportionment of credit scheme, the bucket brigade algorithm (BBA). The DQLCS addresses both of these problems as well as the inherent difficulties faced by learning systems operating in real environments. We introduce Q-learning as the apportionment of credit component of the DQLCS, and we develop a distributed learning architecture to facilitate complex task decomposition. Based upon dynamic programming, the Q-learning update equation is derived and its advantages over the complex BBA are discussed. The distributed architecture is implemented to provide for faster learning by allowing the system to effectively decrease the size of the problem space it must explore. Holistic and monolithic shaping approaches are used to distribute reward among the learning modules of the DQLCS in a variety of real robot learning experiments. The results of these experiments support the DQLCS as a useful reinforcement learning paradigm and suggest future areas of study in distributed learning systems."],"dc:description.degree":["Master of Science"],"dc:format.medium":["BTD"],"dc:format.mimetype":["application/pdf"],"dc:identifier.other":["etd-03042009-041449"],"dc:identifier.uri":["http://hdl.handle.net/10919/41435"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Q-learning","Learning Classifier Systems","artificial intelligence","mobile robots","task decomposition"],"dc:title":["A Distributed Q-learning Classifier System for task decomposition in real robot learning problems"],"dc:type":["Thesis"],"dc:type.dcmitype":["Text"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:26Z"}