{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GJNBHNBEBNYJ7GIJHM7UZAGO65","short_pith_number":"pith:GJNBHNBE","schema_version":"1.0","canonical_sha256":"325a13b4240b709f99093b3f4c80cef77fce0a7d99e08a8294a8091abb499b76","source":{"kind":"arxiv","id":"2209.03993","version":4},"attestation_state":"computed","paper":{"title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Khalil, Raul Santos-Rodriguez (Intelligent System Laboratory, Taku Yamagata, University of Bristol)","submitted_at":"2022-09-08T18:26:39Z","abstract_excerpt":"Recent works have shown that tackling offline reinforcement learning (RL) with a conditional policy produces promising results. The Decision Transformer (DT) combines the conditional policy approach and a transformer architecture, showing competitive performance against several benchmarks. However, DT lacks stitching ability -- one of the critical abilities for offline RL to learn the optimal policy from sub-optimal trajectories. This issue becomes particularly significant when the offline dataset only contains sub-optimal trajectories. On the other hand, the conventional RL approaches based o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.03993","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-08T18:26:39Z","cross_cats_sorted":[],"title_canon_sha256":"1673183cf6ea470db99932bd71b4112edc9874e6cf6e0ff50ce1ce8fb42f4634","abstract_canon_sha256":"ae70f9f0938cdf32a030693140b9c948f8e4c88ea7aa39307895612ee4a6cd59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:53.033308Z","signature_b64":"r1ZwRuYtg5vKJiHi1+do+DfWJC6Ktus0K1xbpfFZE5iFDZ1QfGi4vVcBbv/SmZpbjpn7Dci7Zg9As80bjHAjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"325a13b4240b709f99093b3f4c80cef77fce0a7d99e08a8294a8091abb499b76","last_reissued_at":"2026-07-05T06:13:53.032836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:53.032836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Khalil, Raul Santos-Rodriguez (Intelligent System Laboratory, Taku Yamagata, University of Bristol)","submitted_at":"2022-09-08T18:26:39Z","abstract_excerpt":"Recent works have shown that tackling offline reinforcement learning (RL) with a conditional policy produces promising results. The Decision Transformer (DT) combines the conditional policy approach and a transformer architecture, showing competitive performance against several benchmarks. However, DT lacks stitching ability -- one of the critical abilities for offline RL to learn the optimal policy from sub-optimal trajectories. This issue becomes particularly significant when the offline dataset only contains sub-optimal trajectories. On the other hand, the conventional RL approaches based o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.03993","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.03993/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.03993","created_at":"2026-07-05T06:13:53.032891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.03993v4","created_at":"2026-07-05T06:13:53.032891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.03993","created_at":"2026-07-05T06:13:53.032891+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJNBHNBEBNYJ","created_at":"2026-07-05T06:13:53.032891+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJNBHNBEBNYJ7GIJ","created_at":"2026-07-05T06:13:53.032891+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJNBHNBE","created_at":"2026-07-05T06:13:53.032891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27865","citing_title":"From Bootstrapping to Sequence Modeling: A Unified Generative Framework for Personalized Landing-Page Modeling","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJNBHNBEBNYJ7GIJHM7UZAGO65","json":"https://pith.science/pith/GJNBHNBEBNYJ7GIJHM7UZAGO65.json","graph_json":"https://pith.science/api/pith-number/GJNBHNBEBNYJ7GIJHM7UZAGO65/graph.json","events_json":"https://pith.science/api/pith-number/GJNBHNBEBNYJ7GIJHM7UZAGO65/events.json","paper":"https://pith.science/paper/GJNBHNBE"},"agent_actions":{"view_html":"https://pith.science/pith/GJNBHNBEBNYJ7GIJHM7UZAGO65","download_json":"https://pith.science/pith/GJNBHNBEBNYJ7GIJHM7UZAGO65.json","view_paper":"https://pith.science/paper/GJNBHNBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.03993&json=true","fetch_graph":"https://pith.science/api/pith-number/GJNBHNBEBNYJ7GIJHM7UZAGO65/graph.json","fetch_events":"https://pith.science/api/pith-number/GJNBHNBEBNYJ7GIJHM7UZAGO65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJNBHNBEBNYJ7GIJHM7UZAGO65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJNBHNBEBNYJ7GIJHM7UZAGO65/action/storage_attestation","attest_author":"https://pith.science/pith/GJNBHNBEBNYJ7GIJHM7UZAGO65/action/author_attestation","sign_citation":"https://pith.science/pith/GJNBHNBEBNYJ7GIJHM7UZAGO65/action/citation_signature","submit_replication":"https://pith.science/pith/GJNBHNBEBNYJ7GIJHM7UZAGO65/action/replication_record"}},"created_at":"2026-07-05T06:13:53.032891+00:00","updated_at":"2026-07-05T06:13:53.032891+00:00"}