{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BWXF2TP7K3KJQZSCR5AGE3KAA7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"faa8b5d18f5811defc27ca753c2a2dd33f1b220ed4a2f756792dd95aab9a4912","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T17:57:44Z","title_canon_sha256":"da0ff5cd54dcf65d98cb0f0fa6a47d2132ee710c89f36dbccc78b25c87e6d35c"},"schema_version":"1.0","source":{"id":"2310.04411","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04411","created_at":"2026-07-05T07:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04411v2","created_at":"2026-07-05T07:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04411","created_at":"2026-07-05T07:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"BWXF2TP7K3KJ","created_at":"2026-07-05T07:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"BWXF2TP7K3KJQZSC","created_at":"2026-07-05T07:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"BWXF2TP7","created_at":"2026-07-05T07:09:53Z"}],"graph_snapshots":[{"event_id":"sha256:e42a2284a567b9163a0cb6688e674880805def1a80b4fec0dd60c6ca0561f6e6","target":"graph","created_at":"2026-07-05T07:09:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.04411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bingyi Kang, Gao Huang, Rui Lu, Shiji Song, Yang Yue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T17:57:44Z","title":"Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04411","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fd88bbfbec8f2dee6ffab63f58dacde3f81158f4e621dce1cb566d2410ddc4f4","target":"record","created_at":"2026-07-05T07:09:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"faa8b5d18f5811defc27ca753c2a2dd33f1b220ed4a2f756792dd95aab9a4912","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T17:57:44Z","title_canon_sha256":"da0ff5cd54dcf65d98cb0f0fa6a47d2132ee710c89f36dbccc78b25c87e6d35c"},"schema_version":"1.0","source":{"id":"2310.04411","kind":"arxiv","version":2}},"canonical_sha256":"0dae5d4dff56d49866428f40626d4007cd5da335ff76989f8977dfdaebae7a72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dae5d4dff56d49866428f40626d4007cd5da335ff76989f8977dfdaebae7a72","first_computed_at":"2026-07-05T07:09:53.321277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:53.321277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TNhF8iCaoMtAboJB1GZAKCwWxofP2mxhiiS5htr1XMPlLVMapL6yHrFn71k+Faa5Z+4wh+bb2wSThW5s0WeeDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:53.321783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04411","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd88bbfbec8f2dee6ffab63f58dacde3f81158f4e621dce1cb566d2410ddc4f4","sha256:e42a2284a567b9163a0cb6688e674880805def1a80b4fec0dd60c6ca0561f6e6"],"state_sha256":"0f97e1351497b038d31048580fac6bd1de3b6b2538e29cbb164f8bd47111ac7e"}