{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y5YBKEUA3BQKFDG76XHIKZOS6I","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":"c860d2813a07df0d5caf8e41f99b502f3132628fe3f46fe3f8a7a1c6ee8d5aee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T14:36:51Z","title_canon_sha256":"149048dccff39ec2d2518d88c3155d7f25b207fedcc67e051a0a97705b2db7a6"},"schema_version":"1.0","source":{"id":"2305.18501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18501","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18501v1","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18501","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"Y5YBKEUA3BQK","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"Y5YBKEUA3BQKFDG7","created_at":"2026-07-05T06:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"Y5YBKEUA","created_at":"2026-07-05T06:15:01Z"}],"graph_snapshots":[{"event_id":"sha256:b1e788d6dbed8404970b9e970b956a6e2d3370a1606bdec2ce835be5a941e385","target":"graph","created_at":"2026-07-05T06:15:01Z","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/2305.18501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anna Harutyunyan, Bernardo \\'Avila Pires, Mark Rowland, Michal Valko, R\\'emi Munos, Tadashi Kozuno, Yunhao Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T14:36:51Z","title":"DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18501","kind":"arxiv","version":1},"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":"sha256:6e89dafbaa351aff6a440d223c594240c1d5a5a14cfa04aca4592e17b104392e","target":"record","created_at":"2026-07-05T06:15:01Z","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":"c860d2813a07df0d5caf8e41f99b502f3132628fe3f46fe3f8a7a1c6ee8d5aee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T14:36:51Z","title_canon_sha256":"149048dccff39ec2d2518d88c3155d7f25b207fedcc67e051a0a97705b2db7a6"},"schema_version":"1.0","source":{"id":"2305.18501","kind":"arxiv","version":1}},"canonical_sha256":"c770151280d860a28cdff5ce8565d2f21041fa59eb737c15910c2c61c412491d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c770151280d860a28cdff5ce8565d2f21041fa59eb737c15910c2c61c412491d","first_computed_at":"2026-07-05T06:15:01.719787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:01.719787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1rWqFcUj/JQm8tKPAH6M5AeybVJBnzAbbpRMuimf+FKFQyBH6KXPJtUGAnrFFckBSD/GB/wY3PEhhRB6eB7BBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:01.720269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e89dafbaa351aff6a440d223c594240c1d5a5a14cfa04aca4592e17b104392e","sha256:b1e788d6dbed8404970b9e970b956a6e2d3370a1606bdec2ce835be5a941e385"],"state_sha256":"cfedb8228427dbac68df26c9dd0e751a0a62d632b6da31492d2dcab0ac5ef7a2"}