{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y5YBKEUA3BQKFDG76XHIKZOS6I","short_pith_number":"pith:Y5YBKEUA","schema_version":"1.0","canonical_sha256":"c770151280d860a28cdff5ce8565d2f21041fa59eb737c15910c2c61c412491d","source":{"kind":"arxiv","id":"2305.18501","version":1},"attestation_state":"computed","paper":{"title":"DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anna Harutyunyan, Bernardo \\'Avila Pires, Mark Rowland, Michal Valko, R\\'emi Munos, Tadashi Kozuno, Yunhao Tang","submitted_at":"2023-05-29T14:36:51Z","abstract_excerpt":"Multi-step learning applies lookahead over multiple time steps and has proved valuable in policy evaluation settings. However, in the optimal control case, the impact of multi-step learning has been relatively limited despite a number of prior efforts. Fundamentally, this might be because multi-step policy improvements require operations that cannot be approximated by stochastic samples, hence hindering the widespread adoption of such methods in practice. To address such limitations, we introduce doubly multi-step off-policy VI (DoMo-VI), a novel oracle algorithm that combines multi-step polic"},"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":"2305.18501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T14:36:51Z","cross_cats_sorted":[],"title_canon_sha256":"149048dccff39ec2d2518d88c3155d7f25b207fedcc67e051a0a97705b2db7a6","abstract_canon_sha256":"c860d2813a07df0d5caf8e41f99b502f3132628fe3f46fe3f8a7a1c6ee8d5aee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:01.720269Z","signature_b64":"1rWqFcUj/JQm8tKPAH6M5AeybVJBnzAbbpRMuimf+FKFQyBH6KXPJtUGAnrFFckBSD/GB/wY3PEhhRB6eB7BBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c770151280d860a28cdff5ce8565d2f21041fa59eb737c15910c2c61c412491d","last_reissued_at":"2026-07-05T06:15:01.719787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:01.719787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anna Harutyunyan, Bernardo \\'Avila Pires, Mark Rowland, Michal Valko, R\\'emi Munos, Tadashi Kozuno, Yunhao Tang","submitted_at":"2023-05-29T14:36:51Z","abstract_excerpt":"Multi-step learning applies lookahead over multiple time steps and has proved valuable in policy evaluation settings. However, in the optimal control case, the impact of multi-step learning has been relatively limited despite a number of prior efforts. Fundamentally, this might be because multi-step policy improvements require operations that cannot be approximated by stochastic samples, hence hindering the widespread adoption of such methods in practice. To address such limitations, we introduce doubly multi-step off-policy VI (DoMo-VI), a novel oracle algorithm that combines multi-step polic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18501","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.18501/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":"2305.18501","created_at":"2026-07-05T06:15:01.719846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18501v1","created_at":"2026-07-05T06:15:01.719846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18501","created_at":"2026-07-05T06:15:01.719846+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5YBKEUA3BQK","created_at":"2026-07-05T06:15:01.719846+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5YBKEUA3BQKFDG7","created_at":"2026-07-05T06:15:01.719846+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5YBKEUA","created_at":"2026-07-05T06:15:01.719846+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/Y5YBKEUA3BQKFDG76XHIKZOS6I","json":"https://pith.science/pith/Y5YBKEUA3BQKFDG76XHIKZOS6I.json","graph_json":"https://pith.science/api/pith-number/Y5YBKEUA3BQKFDG76XHIKZOS6I/graph.json","events_json":"https://pith.science/api/pith-number/Y5YBKEUA3BQKFDG76XHIKZOS6I/events.json","paper":"https://pith.science/paper/Y5YBKEUA"},"agent_actions":{"view_html":"https://pith.science/pith/Y5YBKEUA3BQKFDG76XHIKZOS6I","download_json":"https://pith.science/pith/Y5YBKEUA3BQKFDG76XHIKZOS6I.json","view_paper":"https://pith.science/paper/Y5YBKEUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18501&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5YBKEUA3BQKFDG76XHIKZOS6I/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5YBKEUA3BQKFDG76XHIKZOS6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5YBKEUA3BQKFDG76XHIKZOS6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5YBKEUA3BQKFDG76XHIKZOS6I/action/storage_attestation","attest_author":"https://pith.science/pith/Y5YBKEUA3BQKFDG76XHIKZOS6I/action/author_attestation","sign_citation":"https://pith.science/pith/Y5YBKEUA3BQKFDG76XHIKZOS6I/action/citation_signature","submit_replication":"https://pith.science/pith/Y5YBKEUA3BQKFDG76XHIKZOS6I/action/replication_record"}},"created_at":"2026-07-05T06:15:01.719846+00:00","updated_at":"2026-07-05T06:15:01.719846+00:00"}