{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6TMHHMOLWADB2ATIUK64PGSESE","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":"1bc3dcd2a4236c3912703703e265d3698544c8abdc90a405539b42c54fb60124","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T05:59:05Z","title_canon_sha256":"61ae453a812a5528423f68d68200a9743014e230364410ac7f0d864eea06ed16"},"schema_version":"1.0","source":{"id":"2006.06956","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06956","created_at":"2026-07-05T01:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06956v1","created_at":"2026-07-05T01:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06956","created_at":"2026-07-05T01:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"6TMHHMOLWADB","created_at":"2026-07-05T01:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"6TMHHMOLWADB2ATI","created_at":"2026-07-05T01:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"6TMHHMOL","created_at":"2026-07-05T01:09:48Z"}],"graph_snapshots":[{"event_id":"sha256:69d523abe9c74a2d00dd6615674cbddd6258631427ad6b86519f774342035745","target":"graph","created_at":"2026-07-05T01:09:48Z","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/2006.06956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Q-learning with value function approximation may have the poor performance because of overestimation bias and imprecise estimate. Specifically, overestimation bias is from the maximum operator over noise estimate, which is exaggerated using the estimate of a subsequent state. Inspired by the recent advance of deep reinforcement learning and Double Q-learning, we introduce the decorrelated double Q-learning (D2Q). Specifically, we introduce the decorrelated regularization item to reduce the correlation between value function approximators, which can lead to less biased estimation and low varian","authors_text":"Gang Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T05:59:05Z","title":"Decorrelated Double Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06956","kind":"arxiv","version":1},"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:f89aa949071bba9327df242c2fb58aebfcc361d6d3e477e7e662a044b17c3db8","target":"record","created_at":"2026-07-05T01:09:48Z","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":"1bc3dcd2a4236c3912703703e265d3698544c8abdc90a405539b42c54fb60124","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T05:59:05Z","title_canon_sha256":"61ae453a812a5528423f68d68200a9743014e230364410ac7f0d864eea06ed16"},"schema_version":"1.0","source":{"id":"2006.06956","kind":"arxiv","version":1}},"canonical_sha256":"f4d873b1cbb0061d0268a2bdc79a44911288e205894fc567e91d540fd50ac9d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4d873b1cbb0061d0268a2bdc79a44911288e205894fc567e91d540fd50ac9d9","first_computed_at":"2026-07-05T01:09:48.494647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:48.494647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CBnABKXHOj2lmAI7B7bLQT8+MiG/slV7CW9Snksjqe8b9nDQuJ/AEJnHTeR0+tmIBUU+vC9tvJIgP2dRMB1FBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:48.495017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.06956","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f89aa949071bba9327df242c2fb58aebfcc361d6d3e477e7e662a044b17c3db8","sha256:69d523abe9c74a2d00dd6615674cbddd6258631427ad6b86519f774342035745"],"state_sha256":"9c22c74106ec4dbbd96c7f1c93e6c965848d45b4beba906eb9826faf0f4e5b28"}