{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QGKIYCCQ6RWW6LFNTVBFLLZB2G","short_pith_number":"pith:QGKIYCCQ","schema_version":"1.0","canonical_sha256":"81948c0850f46d6f2cad9d4255af21d1bffd3f601cb8410f5e45af7909835241","source":{"kind":"arxiv","id":"2405.17098","version":1},"attestation_state":"computed","paper":{"title":"Q-value Regularized Transformer for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaoqin Huang, Dacheng Tao, Li Shen, Shengchao Hu, Yanfeng Wang, Ya Zhang, Ziqing Fan","submitted_at":"2024-05-27T12:12:39Z","abstract_excerpt":"Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Conditional Sequence Modeling (CSM), a paradigm that learns the action distribution based on history trajectory and target returns for each state. However, these methods often struggle with stitching together optimal trajectories from sub-optimal ones due to the inconsistency between the sampled returns within individual trajectories and the optimal returns across multiple trajectories. Fortunately, Dynamic Programming (DP) methods offer a solution by leveraging a value function to approximate optim"},"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":"2405.17098","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T12:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"d7cabd4239a8691bd17baffc2681f45e3bce6a5732880d34bad62925a2b847c3","abstract_canon_sha256":"88b2d2ac9f082f2e468bd6d2586ea8e96fd797dac343b501bfb052c9c3a99d40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:39.857304Z","signature_b64":"zG4jPyjAFQ8kogidXI6K81O0G9ftcG9YVbOcXcIstw+lASK0U2bT0lGey2JpFm5D7FS8nEk6d5ilmDHV4GYpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81948c0850f46d6f2cad9d4255af21d1bffd3f601cb8410f5e45af7909835241","last_reissued_at":"2026-07-05T08:23:39.856812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:39.856812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-value Regularized Transformer for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaoqin Huang, Dacheng Tao, Li Shen, Shengchao Hu, Yanfeng Wang, Ya Zhang, Ziqing Fan","submitted_at":"2024-05-27T12:12:39Z","abstract_excerpt":"Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Conditional Sequence Modeling (CSM), a paradigm that learns the action distribution based on history trajectory and target returns for each state. However, these methods often struggle with stitching together optimal trajectories from sub-optimal ones due to the inconsistency between the sampled returns within individual trajectories and the optimal returns across multiple trajectories. Fortunately, Dynamic Programming (DP) methods offer a solution by leveraging a value function to approximate optim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17098","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/2405.17098/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":"2405.17098","created_at":"2026-07-05T08:23:39.856875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17098v1","created_at":"2026-07-05T08:23:39.856875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17098","created_at":"2026-07-05T08:23:39.856875+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGKIYCCQ6RWW","created_at":"2026-07-05T08:23:39.856875+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGKIYCCQ6RWW6LFN","created_at":"2026-07-05T08:23:39.856875+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGKIYCCQ","created_at":"2026-07-05T08:23:39.856875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01205","citing_title":"ReBRAC-v2: The Return of the King","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QGKIYCCQ6RWW6LFNTVBFLLZB2G","json":"https://pith.science/pith/QGKIYCCQ6RWW6LFNTVBFLLZB2G.json","graph_json":"https://pith.science/api/pith-number/QGKIYCCQ6RWW6LFNTVBFLLZB2G/graph.json","events_json":"https://pith.science/api/pith-number/QGKIYCCQ6RWW6LFNTVBFLLZB2G/events.json","paper":"https://pith.science/paper/QGKIYCCQ"},"agent_actions":{"view_html":"https://pith.science/pith/QGKIYCCQ6RWW6LFNTVBFLLZB2G","download_json":"https://pith.science/pith/QGKIYCCQ6RWW6LFNTVBFLLZB2G.json","view_paper":"https://pith.science/paper/QGKIYCCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17098&json=true","fetch_graph":"https://pith.science/api/pith-number/QGKIYCCQ6RWW6LFNTVBFLLZB2G/graph.json","fetch_events":"https://pith.science/api/pith-number/QGKIYCCQ6RWW6LFNTVBFLLZB2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGKIYCCQ6RWW6LFNTVBFLLZB2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGKIYCCQ6RWW6LFNTVBFLLZB2G/action/storage_attestation","attest_author":"https://pith.science/pith/QGKIYCCQ6RWW6LFNTVBFLLZB2G/action/author_attestation","sign_citation":"https://pith.science/pith/QGKIYCCQ6RWW6LFNTVBFLLZB2G/action/citation_signature","submit_replication":"https://pith.science/pith/QGKIYCCQ6RWW6LFNTVBFLLZB2G/action/replication_record"}},"created_at":"2026-07-05T08:23:39.856875+00:00","updated_at":"2026-07-05T08:23:39.856875+00:00"}