{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RXCW2X7ZVPMJVZOGO7GAW24LWF","short_pith_number":"pith:RXCW2X7Z","schema_version":"1.0","canonical_sha256":"8dc56d5ff9abd89ae5c677cc0b6b8bb17c05d048635a8a55ac324143340e6992","source":{"kind":"arxiv","id":"1810.05017","version":1},"attestation_state":"computed","paper":{"title":"One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"David Budden, Gabriel Barth-Maron, Matt W. Hoffman, Nando de Freitas, Scott Reed, Sergio G\\'omez Colmenarejo, Serkan Cabi, Tobias Pfaff, Tom Le Paine, Yusuf Aytar, Ziyu Wang","submitted_at":"2018-10-11T13:46:18Z","abstract_excerpt":"Humans are experts at high-fidelity imitation -- closely mimicking a demonstration, often in one attempt. Humans use this ability to quickly solve a task instance, and to bootstrap learning of new tasks. Achieving these abilities in autonomous agents is an open problem. In this paper, we introduce an off-policy RL algorithm (MetaMimic) to narrow this gap. MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators. MetaMimic relies on the principle of storing a"},"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":"1810.05017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T13:46:18Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"628ccceb3a2e49774dc63ab3c322616cb51488427573672ef45cc890586e2bb3","abstract_canon_sha256":"c44ab855f8367176e62d249d39e01353921166424c18f486ccb5a8cfdf1ae9df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:35.213614Z","signature_b64":"78Gw9mGShOS3tMnpWdy/y2JwzHMWF8TdDiLQhI7qMxZG4/hQV452+/xFR9QwCrlFK62jiri1xR24c/yvzhYtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc56d5ff9abd89ae5c677cc0b6b8bb17c05d048635a8a55ac324143340e6992","last_reissued_at":"2026-05-18T00:03:35.213127Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:35.213127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"David Budden, Gabriel Barth-Maron, Matt W. Hoffman, Nando de Freitas, Scott Reed, Sergio G\\'omez Colmenarejo, Serkan Cabi, Tobias Pfaff, Tom Le Paine, Yusuf Aytar, Ziyu Wang","submitted_at":"2018-10-11T13:46:18Z","abstract_excerpt":"Humans are experts at high-fidelity imitation -- closely mimicking a demonstration, often in one attempt. Humans use this ability to quickly solve a task instance, and to bootstrap learning of new tasks. Achieving these abilities in autonomous agents is an open problem. In this paper, we introduce an off-policy RL algorithm (MetaMimic) to narrow this gap. MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators. MetaMimic relies on the principle of storing a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05017","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1810.05017","created_at":"2026-05-18T00:03:35.213198+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.05017v1","created_at":"2026-05-18T00:03:35.213198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05017","created_at":"2026-05-18T00:03:35.213198+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXCW2X7ZVPMJ","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXCW2X7ZVPMJVZOG","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXCW2X7Z","created_at":"2026-05-18T12:32:50.500415+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/RXCW2X7ZVPMJVZOGO7GAW24LWF","json":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF.json","graph_json":"https://pith.science/api/pith-number/RXCW2X7ZVPMJVZOGO7GAW24LWF/graph.json","events_json":"https://pith.science/api/pith-number/RXCW2X7ZVPMJVZOGO7GAW24LWF/events.json","paper":"https://pith.science/paper/RXCW2X7Z"},"agent_actions":{"view_html":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF","download_json":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF.json","view_paper":"https://pith.science/paper/RXCW2X7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.05017&json=true","fetch_graph":"https://pith.science/api/pith-number/RXCW2X7ZVPMJVZOGO7GAW24LWF/graph.json","fetch_events":"https://pith.science/api/pith-number/RXCW2X7ZVPMJVZOGO7GAW24LWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/action/storage_attestation","attest_author":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/action/author_attestation","sign_citation":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/action/citation_signature","submit_replication":"https://pith.science/pith/RXCW2X7ZVPMJVZOGO7GAW24LWF/action/replication_record"}},"created_at":"2026-05-18T00:03:35.213198+00:00","updated_at":"2026-05-18T00:03:35.213198+00:00"}