{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YOGCNHQBK3Y7JNH2WN4LLP2ACK","short_pith_number":"pith:YOGCNHQB","schema_version":"1.0","canonical_sha256":"c38c269e0156f1f4b4fab378b5bf4012b34c365d2686ffdc38bb3b81c4025ba9","source":{"kind":"arxiv","id":"2111.09159","version":3},"attestation_state":"computed","paper":{"title":"Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Che Wang, Keith W. Ross, Xinyue Chen, Yanqiu Wu, Yiming Zhang","submitted_at":"2021-11-17T14:48:52Z","abstract_excerpt":"Recent advances in model-free deep reinforcement learning (DRL) show that simple model-free methods can be highly effective in challenging high-dimensional continuous control tasks. In particular, Truncated Quantile Critics (TQC) achieves state-of-the-art asymptotic training performance on the MuJoCo benchmark with a distributional representation of critics; and Randomized Ensemble Double Q-Learning (REDQ) achieves high sample efficiency that is competitive with state-of-the-art model-based methods using a high update-to-data ratio and target randomization. In this paper, we propose a novel mo"},"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":"2111.09159","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-17T14:48:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43c4fa06d0dc4dd0406e3631aeda074872e381b29cb490be3350a5853c9b8260","abstract_canon_sha256":"122ccf4661d5a773ff62987e60c4c9041808f338b7bb58d031103fcb10c6e7f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:49.655815Z","signature_b64":"s4dKveANIjZkNwLPUPUa49CvIGILL2b7w/o5qpfuRw6yeyycz0i010z01QanpP3jJe8x4VkbXyQg5RY/86+9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c38c269e0156f1f4b4fab378b5bf4012b34c365d2686ffdc38bb3b81c4025ba9","last_reissued_at":"2026-07-05T05:16:49.655388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:49.655388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Che Wang, Keith W. Ross, Xinyue Chen, Yanqiu Wu, Yiming Zhang","submitted_at":"2021-11-17T14:48:52Z","abstract_excerpt":"Recent advances in model-free deep reinforcement learning (DRL) show that simple model-free methods can be highly effective in challenging high-dimensional continuous control tasks. In particular, Truncated Quantile Critics (TQC) achieves state-of-the-art asymptotic training performance on the MuJoCo benchmark with a distributional representation of critics; and Randomized Ensemble Double Q-Learning (REDQ) achieves high sample efficiency that is competitive with state-of-the-art model-based methods using a high update-to-data ratio and target randomization. In this paper, we propose a novel mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09159","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/2111.09159/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":"2111.09159","created_at":"2026-07-05T05:16:49.655445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.09159v3","created_at":"2026-07-05T05:16:49.655445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09159","created_at":"2026-07-05T05:16:49.655445+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOGCNHQBK3Y7","created_at":"2026-07-05T05:16:49.655445+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOGCNHQBK3Y7JNH2","created_at":"2026-07-05T05:16:49.655445+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOGCNHQB","created_at":"2026-07-05T05:16:49.655445+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03194","citing_title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YOGCNHQBK3Y7JNH2WN4LLP2ACK","json":"https://pith.science/pith/YOGCNHQBK3Y7JNH2WN4LLP2ACK.json","graph_json":"https://pith.science/api/pith-number/YOGCNHQBK3Y7JNH2WN4LLP2ACK/graph.json","events_json":"https://pith.science/api/pith-number/YOGCNHQBK3Y7JNH2WN4LLP2ACK/events.json","paper":"https://pith.science/paper/YOGCNHQB"},"agent_actions":{"view_html":"https://pith.science/pith/YOGCNHQBK3Y7JNH2WN4LLP2ACK","download_json":"https://pith.science/pith/YOGCNHQBK3Y7JNH2WN4LLP2ACK.json","view_paper":"https://pith.science/paper/YOGCNHQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.09159&json=true","fetch_graph":"https://pith.science/api/pith-number/YOGCNHQBK3Y7JNH2WN4LLP2ACK/graph.json","fetch_events":"https://pith.science/api/pith-number/YOGCNHQBK3Y7JNH2WN4LLP2ACK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOGCNHQBK3Y7JNH2WN4LLP2ACK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOGCNHQBK3Y7JNH2WN4LLP2ACK/action/storage_attestation","attest_author":"https://pith.science/pith/YOGCNHQBK3Y7JNH2WN4LLP2ACK/action/author_attestation","sign_citation":"https://pith.science/pith/YOGCNHQBK3Y7JNH2WN4LLP2ACK/action/citation_signature","submit_replication":"https://pith.science/pith/YOGCNHQBK3Y7JNH2WN4LLP2ACK/action/replication_record"}},"created_at":"2026-07-05T05:16:49.655445+00:00","updated_at":"2026-07-05T05:16:49.655445+00:00"}