{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XTNWDGFRHCVNGL3SCRO4D6TH54","short_pith_number":"pith:XTNWDGFR","schema_version":"1.0","canonical_sha256":"bcdb6198b138aad32f72145dc1fa67ef122ff7dfa32298ad7a76b981ae871ebc","source":{"kind":"arxiv","id":"2007.15588","version":2},"attestation_state":"computed","paper":{"title":"Data-efficient Hindsight Off-policy Option Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abbas Abdolmaleki, Dhruva Tirumala, Dushyant Rao, Markus Wulfmeier, Martin Riedmiller, Michael Neunert, Nicolas Heess, Noah Siegel, Roland Hafner, Thomas Lampe, Tim Hertweck","submitted_at":"2020-07-30T16:52:33Z","abstract_excerpt":"We introduce Hindsight Off-policy Options (HO2), a data-efficient option learning algorithm. Given any trajectory, HO2 infers likely option choices and backpropagates through the dynamic programming inference procedure to robustly train all policy components off-policy and end-to-end. The approach outperforms existing option learning methods on common benchmarks. To better understand the option framework and disentangle benefits from both temporal and action abstraction, we evaluate ablations with flat policies and mixture policies with comparable optimization. The results highlight the import"},"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":"2007.15588","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-30T16:52:33Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"5021955ea5d6c7d8293a0c738491adef47cf34c5e570c95b4609b4228ed6584e","abstract_canon_sha256":"7ac2a739d257f77e1cdbd3590a773dac319aa06d0b76723e4b5862ab8da47d22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:11.830442Z","signature_b64":"YHnoHPZHnkTPFSL8Gr1rMbPsQv5Xy1zCHzw41nL8mVVhPVQ/5flbkEzzQDObB+VmP8OsfNDWrf5gQdmg/J+TBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcdb6198b138aad32f72145dc1fa67ef122ff7dfa32298ad7a76b981ae871ebc","last_reissued_at":"2026-07-05T02:49:11.829994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:11.829994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-efficient Hindsight Off-policy Option Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abbas Abdolmaleki, Dhruva Tirumala, Dushyant Rao, Markus Wulfmeier, Martin Riedmiller, Michael Neunert, Nicolas Heess, Noah Siegel, Roland Hafner, Thomas Lampe, Tim Hertweck","submitted_at":"2020-07-30T16:52:33Z","abstract_excerpt":"We introduce Hindsight Off-policy Options (HO2), a data-efficient option learning algorithm. Given any trajectory, HO2 infers likely option choices and backpropagates through the dynamic programming inference procedure to robustly train all policy components off-policy and end-to-end. The approach outperforms existing option learning methods on common benchmarks. To better understand the option framework and disentangle benefits from both temporal and action abstraction, we evaluate ablations with flat policies and mixture policies with comparable optimization. The results highlight the import"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.15588","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/2007.15588/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":"2007.15588","created_at":"2026-07-05T02:49:11.830048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.15588v2","created_at":"2026-07-05T02:49:11.830048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.15588","created_at":"2026-07-05T02:49:11.830048+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTNWDGFRHCVN","created_at":"2026-07-05T02:49:11.830048+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTNWDGFRHCVNGL3S","created_at":"2026-07-05T02:49:11.830048+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTNWDGFR","created_at":"2026-07-05T02:49:11.830048+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/XTNWDGFRHCVNGL3SCRO4D6TH54","json":"https://pith.science/pith/XTNWDGFRHCVNGL3SCRO4D6TH54.json","graph_json":"https://pith.science/api/pith-number/XTNWDGFRHCVNGL3SCRO4D6TH54/graph.json","events_json":"https://pith.science/api/pith-number/XTNWDGFRHCVNGL3SCRO4D6TH54/events.json","paper":"https://pith.science/paper/XTNWDGFR"},"agent_actions":{"view_html":"https://pith.science/pith/XTNWDGFRHCVNGL3SCRO4D6TH54","download_json":"https://pith.science/pith/XTNWDGFRHCVNGL3SCRO4D6TH54.json","view_paper":"https://pith.science/paper/XTNWDGFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.15588&json=true","fetch_graph":"https://pith.science/api/pith-number/XTNWDGFRHCVNGL3SCRO4D6TH54/graph.json","fetch_events":"https://pith.science/api/pith-number/XTNWDGFRHCVNGL3SCRO4D6TH54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTNWDGFRHCVNGL3SCRO4D6TH54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTNWDGFRHCVNGL3SCRO4D6TH54/action/storage_attestation","attest_author":"https://pith.science/pith/XTNWDGFRHCVNGL3SCRO4D6TH54/action/author_attestation","sign_citation":"https://pith.science/pith/XTNWDGFRHCVNGL3SCRO4D6TH54/action/citation_signature","submit_replication":"https://pith.science/pith/XTNWDGFRHCVNGL3SCRO4D6TH54/action/replication_record"}},"created_at":"2026-07-05T02:49:11.830048+00:00","updated_at":"2026-07-05T02:49:11.830048+00:00"}