{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/151529"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/151529","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Decision Transformer-based Traveling Salesman Tour Generation","abstract":"With the surge of new machine learning methods, research in classic problems like the Traveling Salesman Problem (TSP) is receiving a resurgence of popularity. One of the biggest goals in this renewed interest is to create a model that can not only outperform state-of-the-art heuristic solvers in speed for trivial sizes, but also generalize to larger TSP instances that are currently intractable. In this thesis we approach the TSP with the Decision Transformer, a transformer-based architecture transforming reinforcement learning environments into transformer-compatible sequence-modeling problems. By modeling a TSP instance as an graph-based environment with states and actions, we can input partial tours into the Decision Transformer to infer the next best action in an autoregressive fashion. With the power of the transformer, we take the first step in making headway on the issue of generalization where past models have failed.","abstract_html":"With the surge of new machine learning methods, research in classic problems like the Traveling Salesman Problem (TSP) is receiving a resurgence of popularity. One of the biggest goals in this renewed interest is to create a model that can not only outperform state-of-the-art heuristic solvers in speed for trivial sizes, but also generalize to larger TSP instances that are currently intractable. In this thesis we approach the TSP with the Decision Transformer, a transformer-based architecture transforming reinforcement learning environments into transformer-compatible sequence-modeling problems. By modeling a TSP instance as an graph-based environment with states and actions, we can input partial tours into the Decision Transformer to infer the next best action in an autoregressive fashion. With the power of the transformer, we take the first step in making headway on the issue of generalization where past models have failed.","abstract_has_math":false,"creators":["Liu, Daniel S."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Balakrishnan, Hamsa"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-06","date_published":"2023-06","updated_at":"2026-07-22T22:22:07Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/151529","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Balakrishnan, Hamsa"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Liu, Daniel S."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-07-31T19:46:35Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-07-31T19:46:35Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-06"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/151529"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["With the surge of new machine learning methods, research in classic problems like the Traveling Salesman Problem (TSP) is receiving a resurgence of popularity. One of the biggest goals in this renewed interest is to create a model that can not only outperform state-of-the-art heuristic solvers in speed for trivial sizes, but also generalize to larger TSP instances that are currently intractable. In this thesis we approach the TSP with the Decision Transformer, a transformer-based architecture transforming reinforcement learning environments into transformer-compatible sequence-modeling problems. By modeling a TSP instance as an graph-based environment with states and actions, we can input partial tours into the Decision Transformer to infer the next best action in an autoregressive fashion. With the power of the transformer, we take the first step in making headway on the issue of generalization where past models have failed."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Decision Transformer-based Traveling Salesman Tour Generation"]}]}],"canonical_facts":{"dc:contributor.advisor":["Balakrishnan, Hamsa"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Liu, Daniel S."],"dc:date.accessioned":["2023-07-31T19:46:35Z"],"dc:date.available":["2023-07-31T19:46:35Z"],"dc:date.issued":["2023-06"],"dc:description.abstract":["With the surge of new machine learning methods, research in classic problems like the Traveling Salesman Problem (TSP) is receiving a resurgence of popularity. One of the biggest goals in this renewed interest is to create a model that can not only outperform state-of-the-art heuristic solvers in speed for trivial sizes, but also generalize to larger TSP instances that are currently intractable. In this thesis we approach the TSP with the Decision Transformer, a transformer-based architecture transforming reinforcement learning environments into transformer-compatible sequence-modeling problems. By modeling a TSP instance as an graph-based environment with states and actions, we can input partial tours into the Decision Transformer to infer the next best action in an autoregressive fashion. With the power of the transformer, we take the first step in making headway on the issue of generalization where past models have failed."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/151529"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Decision Transformer-based Traveling Salesman Tour Generation"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:07Z"}