{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GACEFB24V3TH2QMHUX6B3YPJDH","short_pith_number":"pith:GACEFB24","schema_version":"1.0","canonical_sha256":"300442875caee67d4187a5fc1de1e919c83010487ad94c8d91b200f40fd0409a","source":{"kind":"arxiv","id":"2101.05982","version":2},"attestation_state":"computed","paper":{"title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Che Wang, Keith Ross, Xinyue Chen, Zijian Zhou","submitted_at":"2021-01-15T06:25:58Z","abstract_excerpt":"Using a high Update-To-Data (UTD) ratio, model-based methods have recently achieved much higher sample efficiency than previous model-free methods for continuous-action DRL benchmarks. In this paper, we introduce a simple model-free algorithm, Randomized Ensembled Double Q-Learning (REDQ), and show that its performance is just as good as, if not better than, a state-of-the-art model-based algorithm for the MuJoCo benchmark. Moreover, REDQ can achieve this performance using fewer parameters than the model-based method, and with less wall-clock run time. REDQ has three carefully integrated ingre"},"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":"2101.05982","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-15T06:25:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7401f584a16650c4c6ec5fed82f153687baedc7740202deed7b24b460f7b9c28","abstract_canon_sha256":"2cfc1c21cabec2ea2f778012763fbd723d2fb7379ce476afef606cccca464d64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:13.357781Z","signature_b64":"z12AFdhb9NgGbMirNXDdKqySYpH3qihERDkI4ZqtmtHh9hAucKbCTD9XC83lmJqml2aGxWLuKy0gZQ0Df3DnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"300442875caee67d4187a5fc1de1e919c83010487ad94c8d91b200f40fd0409a","last_reissued_at":"2026-07-05T02:24:13.357350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:13.357350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Che Wang, Keith Ross, Xinyue Chen, Zijian Zhou","submitted_at":"2021-01-15T06:25:58Z","abstract_excerpt":"Using a high Update-To-Data (UTD) ratio, model-based methods have recently achieved much higher sample efficiency than previous model-free methods for continuous-action DRL benchmarks. In this paper, we introduce a simple model-free algorithm, Randomized Ensembled Double Q-Learning (REDQ), and show that its performance is just as good as, if not better than, a state-of-the-art model-based algorithm for the MuJoCo benchmark. Moreover, REDQ can achieve this performance using fewer parameters than the model-based method, and with less wall-clock run time. REDQ has three carefully integrated ingre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.05982","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/2101.05982/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":"2101.05982","created_at":"2026-07-05T02:24:13.357407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.05982v2","created_at":"2026-07-05T02:24:13.357407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.05982","created_at":"2026-07-05T02:24:13.357407+00:00"},{"alias_kind":"pith_short_12","alias_value":"GACEFB24V3TH","created_at":"2026-07-05T02:24:13.357407+00:00"},{"alias_kind":"pith_short_16","alias_value":"GACEFB24V3TH2QMH","created_at":"2026-07-05T02:24:13.357407+00:00"},{"alias_kind":"pith_short_8","alias_value":"GACEFB24","created_at":"2026-07-05T02:24:13.357407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03065","citing_title":"OGPO: Sample Efficient Full-Finetuning of Generative Control Policies","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21822","citing_title":"Implicit Safety Alignment from Crowd Preferences","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03828","citing_title":"From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07986","citing_title":"EXPO: Stable Reinforcement Learning with Expressive Policies","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03828","citing_title":"From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23073","citing_title":"RL Token: Bootstrapping Online RL with Vision-Language-Action Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20381","citing_title":"Distributional Value Estimation Without Target Networks for Robust Quality-Diversity","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03065","citing_title":"OGPO: Sample Efficient Full-Finetuning of Generative Control Policies","ref_index":139,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GACEFB24V3TH2QMHUX6B3YPJDH","json":"https://pith.science/pith/GACEFB24V3TH2QMHUX6B3YPJDH.json","graph_json":"https://pith.science/api/pith-number/GACEFB24V3TH2QMHUX6B3YPJDH/graph.json","events_json":"https://pith.science/api/pith-number/GACEFB24V3TH2QMHUX6B3YPJDH/events.json","paper":"https://pith.science/paper/GACEFB24"},"agent_actions":{"view_html":"https://pith.science/pith/GACEFB24V3TH2QMHUX6B3YPJDH","download_json":"https://pith.science/pith/GACEFB24V3TH2QMHUX6B3YPJDH.json","view_paper":"https://pith.science/paper/GACEFB24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.05982&json=true","fetch_graph":"https://pith.science/api/pith-number/GACEFB24V3TH2QMHUX6B3YPJDH/graph.json","fetch_events":"https://pith.science/api/pith-number/GACEFB24V3TH2QMHUX6B3YPJDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GACEFB24V3TH2QMHUX6B3YPJDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GACEFB24V3TH2QMHUX6B3YPJDH/action/storage_attestation","attest_author":"https://pith.science/pith/GACEFB24V3TH2QMHUX6B3YPJDH/action/author_attestation","sign_citation":"https://pith.science/pith/GACEFB24V3TH2QMHUX6B3YPJDH/action/citation_signature","submit_replication":"https://pith.science/pith/GACEFB24V3TH2QMHUX6B3YPJDH/action/replication_record"}},"created_at":"2026-07-05T02:24:13.357407+00:00","updated_at":"2026-07-05T02:24:13.357407+00:00"}