{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XWFJABMAIGCZBZI3WTOXLM7M3Y","short_pith_number":"pith:XWFJABMA","schema_version":"1.0","canonical_sha256":"bd8a900580418590e51bb4dd75b3ecde16dabb2556af6c6afaf21be0a158111a","source":{"kind":"arxiv","id":"2304.08487","version":1},"attestation_state":"computed","paper":{"title":"Hyper-Decision Transformer for Efficient Online Policy Adaptation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chuang Gan, Ding Zhao, Mengdi Xu, Shun Zhang, Yikang Shen, Yuchen Lu","submitted_at":"2023-04-17T17:59:32Z","abstract_excerpt":"Decision Transformers (DT) have demonstrated strong performances in offline reinforcement learning settings, but quickly adapting to unseen novel tasks remains challenging. To address this challenge, we propose a new framework, called Hyper-Decision Transformer (HDT), that can generalize to novel tasks from a handful of demonstrations in a data- and parameter-efficient manner. To achieve such a goal, we propose to augment the base DT with an adaptation module, whose parameters are initialized by a hyper-network. When encountering unseen tasks, the hyper-network takes a handful of demonstration"},"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":"2304.08487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T17:59:32Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"ec440fa4c1da7e7ced8da60ba3290efa56ba810cdb32733f2a4e18dbf593a218","abstract_canon_sha256":"6a16363983044e81209f76ba9e820953d4678e4f40bcbbd14e554604b1a3979c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:52.968844Z","signature_b64":"nF9y2SuJhbW25JpjPIOpJYAAfRQBN9SXiPgWKE6M7LY7jICCI09zTcsoFN9Ge8p0JUMMWmupc4vUFHrwLE/qBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd8a900580418590e51bb4dd75b3ecde16dabb2556af6c6afaf21be0a158111a","last_reissued_at":"2026-07-05T06:01:52.968387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:52.968387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyper-Decision Transformer for Efficient Online Policy Adaptation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chuang Gan, Ding Zhao, Mengdi Xu, Shun Zhang, Yikang Shen, Yuchen Lu","submitted_at":"2023-04-17T17:59:32Z","abstract_excerpt":"Decision Transformers (DT) have demonstrated strong performances in offline reinforcement learning settings, but quickly adapting to unseen novel tasks remains challenging. To address this challenge, we propose a new framework, called Hyper-Decision Transformer (HDT), that can generalize to novel tasks from a handful of demonstrations in a data- and parameter-efficient manner. To achieve such a goal, we propose to augment the base DT with an adaptation module, whose parameters are initialized by a hyper-network. When encountering unseen tasks, the hyper-network takes a handful of demonstration"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08487","kind":"arxiv","version":1},"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/2304.08487/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":"2304.08487","created_at":"2026-07-05T06:01:52.968444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08487v1","created_at":"2026-07-05T06:01:52.968444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08487","created_at":"2026-07-05T06:01:52.968444+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWFJABMAIGCZ","created_at":"2026-07-05T06:01:52.968444+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWFJABMAIGCZBZI3","created_at":"2026-07-05T06:01:52.968444+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWFJABMA","created_at":"2026-07-05T06:01:52.968444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18979","citing_title":"TabQL: In-Context Q-Learning with Tabular Foundation Models","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XWFJABMAIGCZBZI3WTOXLM7M3Y","json":"https://pith.science/pith/XWFJABMAIGCZBZI3WTOXLM7M3Y.json","graph_json":"https://pith.science/api/pith-number/XWFJABMAIGCZBZI3WTOXLM7M3Y/graph.json","events_json":"https://pith.science/api/pith-number/XWFJABMAIGCZBZI3WTOXLM7M3Y/events.json","paper":"https://pith.science/paper/XWFJABMA"},"agent_actions":{"view_html":"https://pith.science/pith/XWFJABMAIGCZBZI3WTOXLM7M3Y","download_json":"https://pith.science/pith/XWFJABMAIGCZBZI3WTOXLM7M3Y.json","view_paper":"https://pith.science/paper/XWFJABMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08487&json=true","fetch_graph":"https://pith.science/api/pith-number/XWFJABMAIGCZBZI3WTOXLM7M3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/XWFJABMAIGCZBZI3WTOXLM7M3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWFJABMAIGCZBZI3WTOXLM7M3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWFJABMAIGCZBZI3WTOXLM7M3Y/action/storage_attestation","attest_author":"https://pith.science/pith/XWFJABMAIGCZBZI3WTOXLM7M3Y/action/author_attestation","sign_citation":"https://pith.science/pith/XWFJABMAIGCZBZI3WTOXLM7M3Y/action/citation_signature","submit_replication":"https://pith.science/pith/XWFJABMAIGCZBZI3WTOXLM7M3Y/action/replication_record"}},"created_at":"2026-07-05T06:01:52.968444+00:00","updated_at":"2026-07-05T06:01:52.968444+00:00"}