{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4PPB44T2PEPZCWUZQMZ4X26Y6I","short_pith_number":"pith:4PPB44T2","schema_version":"1.0","canonical_sha256":"e3de1e727a791f915a998333cbebd8f237c0d2b2a00ccb8e540309472e7803da","source":{"kind":"arxiv","id":"2103.00445","version":2},"attestation_state":"computed","paper":{"title":"Ensemble Bootstrapping for Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Tessler, Nadav Merlis, Oren Peer, Ron Meir","submitted_at":"2021-02-28T10:19:47Z","abstract_excerpt":"Q-learning (QL), a common reinforcement learning algorithm, suffers from over-estimation bias due to the maximization term in the optimal Bellman operator. This bias may lead to sub-optimal behavior. Double-Q-learning tackles this issue by utilizing two estimators, yet results in an under-estimation bias. Similar to over-estimation in Q-learning, in certain scenarios, the under-estimation bias may degrade performance. In this work, we introduce a new bias-reduced algorithm called Ensemble Bootstrapped Q-Learning (EBQL), a natural extension of Double-Q-learning to ensembles. We analyze our meth"},"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":"2103.00445","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-28T10:19:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0abd8fc03a20877fc021fc8b56348a7e96a04e2ca77f23435c945893acbb02ae","abstract_canon_sha256":"277b0e5e551fa12c04f7a5806f497f32f82aaa5e3b714ca3817efba4b63f2ea4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:29.942669Z","signature_b64":"gCS/ZREVZyakije2n79k/kOTRe2Szupc8SqMp76m/PGBmXfc8CaH/EGosQrxOdtbIOuYGMFwViXdznWVri4DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3de1e727a791f915a998333cbebd8f237c0d2b2a00ccb8e540309472e7803da","last_reissued_at":"2026-07-05T02:33:29.942184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:29.942184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble Bootstrapping for Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Tessler, Nadav Merlis, Oren Peer, Ron Meir","submitted_at":"2021-02-28T10:19:47Z","abstract_excerpt":"Q-learning (QL), a common reinforcement learning algorithm, suffers from over-estimation bias due to the maximization term in the optimal Bellman operator. This bias may lead to sub-optimal behavior. Double-Q-learning tackles this issue by utilizing two estimators, yet results in an under-estimation bias. Similar to over-estimation in Q-learning, in certain scenarios, the under-estimation bias may degrade performance. In this work, we introduce a new bias-reduced algorithm called Ensemble Bootstrapped Q-Learning (EBQL), a natural extension of Double-Q-learning to ensembles. We analyze our meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00445","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/2103.00445/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":"2103.00445","created_at":"2026-07-05T02:33:29.942241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.00445v2","created_at":"2026-07-05T02:33:29.942241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00445","created_at":"2026-07-05T02:33:29.942241+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PPB44T2PEPZ","created_at":"2026-07-05T02:33:29.942241+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PPB44T2PEPZCWUZ","created_at":"2026-07-05T02:33:29.942241+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PPB44T2","created_at":"2026-07-05T02:33:29.942241+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04815","citing_title":"An Arbitration Control for an Ensemble of Diversified DQN variants in Continual Reinforcement Learning","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4PPB44T2PEPZCWUZQMZ4X26Y6I","json":"https://pith.science/pith/4PPB44T2PEPZCWUZQMZ4X26Y6I.json","graph_json":"https://pith.science/api/pith-number/4PPB44T2PEPZCWUZQMZ4X26Y6I/graph.json","events_json":"https://pith.science/api/pith-number/4PPB44T2PEPZCWUZQMZ4X26Y6I/events.json","paper":"https://pith.science/paper/4PPB44T2"},"agent_actions":{"view_html":"https://pith.science/pith/4PPB44T2PEPZCWUZQMZ4X26Y6I","download_json":"https://pith.science/pith/4PPB44T2PEPZCWUZQMZ4X26Y6I.json","view_paper":"https://pith.science/paper/4PPB44T2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.00445&json=true","fetch_graph":"https://pith.science/api/pith-number/4PPB44T2PEPZCWUZQMZ4X26Y6I/graph.json","fetch_events":"https://pith.science/api/pith-number/4PPB44T2PEPZCWUZQMZ4X26Y6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PPB44T2PEPZCWUZQMZ4X26Y6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PPB44T2PEPZCWUZQMZ4X26Y6I/action/storage_attestation","attest_author":"https://pith.science/pith/4PPB44T2PEPZCWUZQMZ4X26Y6I/action/author_attestation","sign_citation":"https://pith.science/pith/4PPB44T2PEPZCWUZQMZ4X26Y6I/action/citation_signature","submit_replication":"https://pith.science/pith/4PPB44T2PEPZCWUZQMZ4X26Y6I/action/replication_record"}},"created_at":"2026-07-05T02:33:29.942241+00:00","updated_at":"2026-07-05T02:33:29.942241+00:00"}