{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BWXF2TP7K3KJQZSCR5AGE3KAA7","short_pith_number":"pith:BWXF2TP7","schema_version":"1.0","canonical_sha256":"0dae5d4dff56d49866428f40626d4007cd5da335ff76989f8977dfdaebae7a72","source":{"kind":"arxiv","id":"2310.04411","version":2},"attestation_state":"computed","paper":{"title":"Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingyi Kang, Gao Huang, Rui Lu, Shiji Song, Yang Yue","submitted_at":"2023-10-06T17:57:44Z","abstract_excerpt":"The divergence of the Q-value estimation has been a prominent issue in offline RL, where the agent has no access to real dynamics. Traditional beliefs attribute this instability to querying out-of-distribution actions when bootstrapping value targets. Though this issue can be alleviated with policy constraints or conservative Q estimation, a theoretical understanding of the underlying mechanism causing the divergence has been absent. In this work, we aim to thoroughly comprehend this mechanism and attain an improved solution. We first identify a fundamental pattern, self-excitation, as the pri"},"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":"2310.04411","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T17:57:44Z","cross_cats_sorted":[],"title_canon_sha256":"da0ff5cd54dcf65d98cb0f0fa6a47d2132ee710c89f36dbccc78b25c87e6d35c","abstract_canon_sha256":"faa8b5d18f5811defc27ca753c2a2dd33f1b220ed4a2f756792dd95aab9a4912"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:53.321783Z","signature_b64":"TNhF8iCaoMtAboJB1GZAKCwWxofP2mxhiiS5htr1XMPlLVMapL6yHrFn71k+Faa5Z+4wh+bb2wSThW5s0WeeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dae5d4dff56d49866428f40626d4007cd5da335ff76989f8977dfdaebae7a72","last_reissued_at":"2026-07-05T07:09:53.321277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:53.321277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingyi Kang, Gao Huang, Rui Lu, Shiji Song, Yang Yue","submitted_at":"2023-10-06T17:57:44Z","abstract_excerpt":"The divergence of the Q-value estimation has been a prominent issue in offline RL, where the agent has no access to real dynamics. Traditional beliefs attribute this instability to querying out-of-distribution actions when bootstrapping value targets. Though this issue can be alleviated with policy constraints or conservative Q estimation, a theoretical understanding of the underlying mechanism causing the divergence has been absent. In this work, we aim to thoroughly comprehend this mechanism and attain an improved solution. We first identify a fundamental pattern, self-excitation, as the pri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04411","kind":"arxiv","version":2},"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/2310.04411/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":"2310.04411","created_at":"2026-07-05T07:09:53.321343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04411v2","created_at":"2026-07-05T07:09:53.321343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04411","created_at":"2026-07-05T07:09:53.321343+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWXF2TP7K3KJ","created_at":"2026-07-05T07:09:53.321343+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWXF2TP7K3KJQZSC","created_at":"2026-07-05T07:09:53.321343+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWXF2TP7","created_at":"2026-07-05T07:09:53.321343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18855","citing_title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWXF2TP7K3KJQZSCR5AGE3KAA7","json":"https://pith.science/pith/BWXF2TP7K3KJQZSCR5AGE3KAA7.json","graph_json":"https://pith.science/api/pith-number/BWXF2TP7K3KJQZSCR5AGE3KAA7/graph.json","events_json":"https://pith.science/api/pith-number/BWXF2TP7K3KJQZSCR5AGE3KAA7/events.json","paper":"https://pith.science/paper/BWXF2TP7"},"agent_actions":{"view_html":"https://pith.science/pith/BWXF2TP7K3KJQZSCR5AGE3KAA7","download_json":"https://pith.science/pith/BWXF2TP7K3KJQZSCR5AGE3KAA7.json","view_paper":"https://pith.science/paper/BWXF2TP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04411&json=true","fetch_graph":"https://pith.science/api/pith-number/BWXF2TP7K3KJQZSCR5AGE3KAA7/graph.json","fetch_events":"https://pith.science/api/pith-number/BWXF2TP7K3KJQZSCR5AGE3KAA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWXF2TP7K3KJQZSCR5AGE3KAA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWXF2TP7K3KJQZSCR5AGE3KAA7/action/storage_attestation","attest_author":"https://pith.science/pith/BWXF2TP7K3KJQZSCR5AGE3KAA7/action/author_attestation","sign_citation":"https://pith.science/pith/BWXF2TP7K3KJQZSCR5AGE3KAA7/action/citation_signature","submit_replication":"https://pith.science/pith/BWXF2TP7K3KJQZSCR5AGE3KAA7/action/replication_record"}},"created_at":"2026-07-05T07:09:53.321343+00:00","updated_at":"2026-07-05T07:09:53.321343+00:00"}