{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:F3C3PEKCNH7EXYTNVQEHNUCJLR","short_pith_number":"pith:F3C3PEKC","schema_version":"1.0","canonical_sha256":"2ec5b7914269fe4be26dac0876d0495c592ad931d0648c4409a1da9a32af6898","source":{"kind":"arxiv","id":"2006.13823","version":3},"attestation_state":"computed","paper":{"title":"Preventing Value Function Collapse in Ensemble {Q}-Learning by Maximizing Representation Diversity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hassam Ullah Sheikh, Ladislau B\\\"ol\\\"oni","submitted_at":"2020-06-24T15:53:20Z","abstract_excerpt":"The classic DQN algorithm is limited by the overestimation bias of the learned Q-function. Subsequent algorithms have proposed techniques to reduce this problem, without fully eliminating it. Recently, the Maxmin and Ensemble Q-learning algorithms have used different estimates provided by the ensembles of learners to reduce the overestimation bias. Unfortunately, these learners can converge to the same point in the parametric or representation space, falling back to the classic single neural network DQN. In this paper, we describe a regularization technique to maximize ensemble diversity in th"},"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":"2006.13823","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T15:53:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e385ba023b17e8db54f72e5f537e13d948ceacb9173fcc88f5cd6c302b598e3d","abstract_canon_sha256":"95142d26add4f2614255dd81b9c69514911b5d2c5834bea069ce4c31a14aae7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:12.899888Z","signature_b64":"bZ3NDpT+iP40p6IDxcN73y78KvhmHUrgMhe7A/gKPVvlpxZ8FJw//5prj0SkAypyUniHDCJd8zLgm10u8WgJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ec5b7914269fe4be26dac0876d0495c592ad931d0648c4409a1da9a32af6898","last_reissued_at":"2026-07-05T03:50:12.899411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:12.899411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preventing Value Function Collapse in Ensemble {Q}-Learning by Maximizing Representation Diversity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hassam Ullah Sheikh, Ladislau B\\\"ol\\\"oni","submitted_at":"2020-06-24T15:53:20Z","abstract_excerpt":"The classic DQN algorithm is limited by the overestimation bias of the learned Q-function. Subsequent algorithms have proposed techniques to reduce this problem, without fully eliminating it. Recently, the Maxmin and Ensemble Q-learning algorithms have used different estimates provided by the ensembles of learners to reduce the overestimation bias. Unfortunately, these learners can converge to the same point in the parametric or representation space, falling back to the classic single neural network DQN. In this paper, we describe a regularization technique to maximize ensemble diversity in th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13823","kind":"arxiv","version":3},"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/2006.13823/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":"2006.13823","created_at":"2026-07-05T03:50:12.899468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.13823v3","created_at":"2026-07-05T03:50:12.899468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13823","created_at":"2026-07-05T03:50:12.899468+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3C3PEKCNH7E","created_at":"2026-07-05T03:50:12.899468+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3C3PEKCNH7EXYTN","created_at":"2026-07-05T03:50:12.899468+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3C3PEKC","created_at":"2026-07-05T03:50:12.899468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3C3PEKCNH7EXYTNVQEHNUCJLR","json":"https://pith.science/pith/F3C3PEKCNH7EXYTNVQEHNUCJLR.json","graph_json":"https://pith.science/api/pith-number/F3C3PEKCNH7EXYTNVQEHNUCJLR/graph.json","events_json":"https://pith.science/api/pith-number/F3C3PEKCNH7EXYTNVQEHNUCJLR/events.json","paper":"https://pith.science/paper/F3C3PEKC"},"agent_actions":{"view_html":"https://pith.science/pith/F3C3PEKCNH7EXYTNVQEHNUCJLR","download_json":"https://pith.science/pith/F3C3PEKCNH7EXYTNVQEHNUCJLR.json","view_paper":"https://pith.science/paper/F3C3PEKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.13823&json=true","fetch_graph":"https://pith.science/api/pith-number/F3C3PEKCNH7EXYTNVQEHNUCJLR/graph.json","fetch_events":"https://pith.science/api/pith-number/F3C3PEKCNH7EXYTNVQEHNUCJLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3C3PEKCNH7EXYTNVQEHNUCJLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3C3PEKCNH7EXYTNVQEHNUCJLR/action/storage_attestation","attest_author":"https://pith.science/pith/F3C3PEKCNH7EXYTNVQEHNUCJLR/action/author_attestation","sign_citation":"https://pith.science/pith/F3C3PEKCNH7EXYTNVQEHNUCJLR/action/citation_signature","submit_replication":"https://pith.science/pith/F3C3PEKCNH7EXYTNVQEHNUCJLR/action/replication_record"}},"created_at":"2026-07-05T03:50:12.899468+00:00","updated_at":"2026-07-05T03:50:12.899468+00:00"}