{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4PPB44T2PEPZCWUZQMZ4X26Y6I","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":"277b0e5e551fa12c04f7a5806f497f32f82aaa5e3b714ca3817efba4b63f2ea4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-28T10:19:47Z","title_canon_sha256":"0abd8fc03a20877fc021fc8b56348a7e96a04e2ca77f23435c945893acbb02ae"},"schema_version":"1.0","source":{"id":"2103.00445","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.00445","created_at":"2026-07-05T02:33:29Z"},{"alias_kind":"arxiv_version","alias_value":"2103.00445v2","created_at":"2026-07-05T02:33:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00445","created_at":"2026-07-05T02:33:29Z"},{"alias_kind":"pith_short_12","alias_value":"4PPB44T2PEPZ","created_at":"2026-07-05T02:33:29Z"},{"alias_kind":"pith_short_16","alias_value":"4PPB44T2PEPZCWUZ","created_at":"2026-07-05T02:33:29Z"},{"alias_kind":"pith_short_8","alias_value":"4PPB44T2","created_at":"2026-07-05T02:33:29Z"}],"graph_snapshots":[{"event_id":"sha256:c4d6dbb1afa2f81de59306d79a56200dd4c198023002e75ff879143a2872168a","target":"graph","created_at":"2026-07-05T02:33:29Z","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/2103.00445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chen Tessler, Nadav Merlis, Oren Peer, Ron Meir","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-28T10:19:47Z","title":"Ensemble Bootstrapping for Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00445","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":"sha256:57d05ab5a9184dc7ad826f6c437b435928f46a6930bad73d1f4b41fb8dab6505","target":"record","created_at":"2026-07-05T02:33:29Z","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":"277b0e5e551fa12c04f7a5806f497f32f82aaa5e3b714ca3817efba4b63f2ea4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-28T10:19:47Z","title_canon_sha256":"0abd8fc03a20877fc021fc8b56348a7e96a04e2ca77f23435c945893acbb02ae"},"schema_version":"1.0","source":{"id":"2103.00445","kind":"arxiv","version":2}},"canonical_sha256":"e3de1e727a791f915a998333cbebd8f237c0d2b2a00ccb8e540309472e7803da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3de1e727a791f915a998333cbebd8f237c0d2b2a00ccb8e540309472e7803da","first_computed_at":"2026-07-05T02:33:29.942184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:29.942184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gCS/ZREVZyakije2n79k/kOTRe2Szupc8SqMp76m/PGBmXfc8CaH/EGosQrxOdtbIOuYGMFwViXdznWVri4DAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:29.942669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.00445","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57d05ab5a9184dc7ad826f6c437b435928f46a6930bad73d1f4b41fb8dab6505","sha256:c4d6dbb1afa2f81de59306d79a56200dd4c198023002e75ff879143a2872168a"],"state_sha256":"c4d53616cbdf6ec5540837cb4903e628dd69eab6531bb7d57790e21278eefbad"}