{"id":{"repo_id":"uoit","oai_identifier":"oai:ontariotechu.scholaris.ca:10155/1960"},"canonical_url":"https://search.dev.ndltd.org/etd/uoit/oai:ontariotechu.scholaris.ca:10155/1960","repository":{"repo_id":"uoit","name":"Ontario Institute of Technology","base_url":"https://ontariotechu.scholaris.ca/server/oai/request"},"display":{"title":"Quasimetric decision transformer: enhancing goal-conditioned reinforcement learning with structured distance guidance","abstract":"Recent works have shown that tackling offline Reinforcement Learning (RL) with a conditional policy produces promising results. Decision Transformer (DT) have shown promising results in offline RL by leveraging sequence modeling. However, standard DTs rely on Returns-to-Go (RTG) tokens, which are heuristically defined and often suboptimal for goal-conditioned tasks. In this work, we introduce Quasimetric Decision Transformer (QuaD), a novel approach that replaces RTG with learned quasimetric distances, providing a more structured and theoretically grounded guidance signal for long-horizon decision-making. We explore two quasimetric formulations: Interval Quasimetric Embedding (IQE) and Metric Residual Network (MRN), and integrate them into DTs. Extensive evaluations on the AntMaze benchmark demonstrate that QuaD outperforms standard DTs, achieving state-of-the-art success rates and improved generalization to unseen goals. Our results suggest that quasimetric guidance is a viable alternative to RTG, opening new directions for learning structured distance representations in offline RL.","abstract_html":"Recent works have shown that tackling offline Reinforcement Learning (RL) with a conditional policy produces promising results. Decision Transformer (DT) have shown promising results in offline RL by leveraging sequence modeling. However, standard DTs rely on Returns-to-Go (RTG) tokens, which are heuristically defined and often suboptimal for goal-conditioned tasks. In this work, we introduce Quasimetric Decision Transformer (QuaD), a novel approach that replaces RTG with learned quasimetric distances, providing a more structured and theoretically grounded guidance signal for long-horizon decision-making. We explore two quasimetric formulations: Interval Quasimetric Embedding (IQE) and Metric Residual Network (MRN), and integrate them into DTs. Extensive evaluations on the AntMaze benchmark demonstrate that QuaD outperforms standard DTs, achieving state-of-the-art success rates and improved generalization to unseen goals. Our results suggest that quasimetric guidance is a viable alternative to RTG, opening new directions for learning structured distance representations in offline RL.","abstract_has_math":false,"creators":["Goyani, Madhav"],"institution":"University of Ontario Institute of Technology","degree_name":"Master of Science (MSc)","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Ebrahimi, Mehran","Davoudi, Kourosh"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05-01","date_published":"2025-05-01","updated_at":"2026-07-24T05:35:32Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10155/1960","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Ebrahimi, Mehran","Davoudi, Kourosh"]},{"key":"dc:creator","label":"Author","values":["Goyani, Madhav"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-07-21T14:12:44Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-07-21T14:12:44Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05-01"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MSc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Ontario Institute of Technology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10155/1960"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Recent works have shown that tackling offline Reinforcement Learning (RL) with a conditional policy produces promising results. Decision Transformer (DT) have shown promising results in offline RL by leveraging sequence modeling. However, standard DTs rely on Returns-to-Go (RTG) tokens, which are heuristically defined and often suboptimal for goal-conditioned tasks. In this work, we introduce Quasimetric Decision Transformer (QuaD), a novel approach that replaces RTG with learned quasimetric distances, providing a more structured and theoretically grounded guidance signal for long-horizon decision-making. We explore two quasimetric formulations: Interval Quasimetric Embedding (IQE) and Metric Residual Network (MRN), and integrate them into DTs. Extensive evaluations on the AntMaze benchmark demonstrate that QuaD outperforms standard DTs, achieving state-of-the-art success rates and improved generalization to unseen goals. Our results suggest that quasimetric guidance is a viable alternative to RTG, opening new directions for learning structured distance representations in offline RL."]},{"key":"dc:title","label":"Title","values":["Quasimetric decision transformer: enhancing goal-conditioned reinforcement learning with structured distance guidance"]}]}],"canonical_facts":{"dc:contributor.advisor":["Ebrahimi, Mehran","Davoudi, Kourosh"],"dc:creator":["Goyani, Madhav"],"dc:date.accessioned":["2025-07-21T14:12:44Z"],"dc:date.available":["2025-07-21T14:12:44Z"],"dc:date.issued":["2025-05-01"],"dc:description.abstract":["Recent works have shown that tackling offline Reinforcement Learning (RL) with a conditional policy produces promising results. Decision Transformer (DT) have shown promising results in offline RL by leveraging sequence modeling. However, standard DTs rely on Returns-to-Go (RTG) tokens, which are heuristically defined and often suboptimal for goal-conditioned tasks. In this work, we introduce Quasimetric Decision Transformer (QuaD), a novel approach that replaces RTG with learned quasimetric distances, providing a more structured and theoretically grounded guidance signal for long-horizon decision-making. We explore two quasimetric formulations: Interval Quasimetric Embedding (IQE) and Metric Residual Network (MRN), and integrate them into DTs. Extensive evaluations on the AntMaze benchmark demonstrate that QuaD outperforms standard DTs, achieving state-of-the-art success rates and improved generalization to unseen goals. Our results suggest that quasimetric guidance is a viable alternative to RTG, opening new directions for learning structured distance representations in offline RL."],"dc:identifier.uri":["https://hdl.handle.net/10155/1960"],"dc:language.iso":["en"],"dc:title":["Quasimetric decision transformer: enhancing goal-conditioned reinforcement learning with structured distance guidance"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Master of Science (MSc)"],"thesis:institution_name":["University of Ontario Institute of Technology"]},"updated_at":"2026-07-24T05:35:32Z"}