{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7SVZT6I7NMFN7GAYHUUUNWARZQ","short_pith_number":"pith:7SVZT6I7","schema_version":"1.0","canonical_sha256":"fcab99f91f6b0adf98183d2946d811cc0c4cfa03d118b73fcdfa1a014219139e","source":{"kind":"arxiv","id":"1812.01488","version":1},"attestation_state":"computed","paper":{"title":"Natural Option Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Philip S. Thomas, Saket Tiwari","submitted_at":"2018-12-04T15:33:26Z","abstract_excerpt":"The recently proposed option-critic architecture Bacon et al. provide a stochastic policy gradient approach to hierarchical reinforcement learning. Specifically, they provide a way to estimate the gradient of the expected discounted return with respect to parameters that define a finite number of temporally extended actions, called \\textit{options}. In this paper we show how the option-critic architecture can be extended to estimate the natural gradient of the expected discounted return. To this end, the central questions that we consider in this paper are: 1) what is the definition of the nat"},"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":"1812.01488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:33:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"217aef5f7b16ec8c9fd6b36a9cbbca8276f570047d6ebb9921e9638622efa386","abstract_canon_sha256":"ffa0241c727cda61d3a5263a7fc36b0ec3ec6a6292402abd378de3c234c3b56d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:12.335574Z","signature_b64":"H+RI7sVX2zCk8uNIyVKr7sgndDoW5po51d35bROHLa9K75h9Y05HQ5kna/KoDYDwBVT5WtKhY8TBNtvwIcsWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcab99f91f6b0adf98183d2946d811cc0c4cfa03d118b73fcdfa1a014219139e","last_reissued_at":"2026-05-17T23:59:12.335063Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:12.335063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Natural Option Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Philip S. Thomas, Saket Tiwari","submitted_at":"2018-12-04T15:33:26Z","abstract_excerpt":"The recently proposed option-critic architecture Bacon et al. provide a stochastic policy gradient approach to hierarchical reinforcement learning. Specifically, they provide a way to estimate the gradient of the expected discounted return with respect to parameters that define a finite number of temporally extended actions, called \\textit{options}. In this paper we show how the option-critic architecture can be extended to estimate the natural gradient of the expected discounted return. To this end, the central questions that we consider in this paper are: 1) what is the definition of the nat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01488","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":"1812.01488","created_at":"2026-05-17T23:59:12.335146+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01488v1","created_at":"2026-05-17T23:59:12.335146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01488","created_at":"2026-05-17T23:59:12.335146+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SVZT6I7NMFN","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SVZT6I7NMFN7GAY","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SVZT6I7","created_at":"2026-05-18T12:32:11.075285+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/7SVZT6I7NMFN7GAYHUUUNWARZQ","json":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ.json","graph_json":"https://pith.science/api/pith-number/7SVZT6I7NMFN7GAYHUUUNWARZQ/graph.json","events_json":"https://pith.science/api/pith-number/7SVZT6I7NMFN7GAYHUUUNWARZQ/events.json","paper":"https://pith.science/paper/7SVZT6I7"},"agent_actions":{"view_html":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ","download_json":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ.json","view_paper":"https://pith.science/paper/7SVZT6I7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01488&json=true","fetch_graph":"https://pith.science/api/pith-number/7SVZT6I7NMFN7GAYHUUUNWARZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7SVZT6I7NMFN7GAYHUUUNWARZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/action/storage_attestation","attest_author":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/action/author_attestation","sign_citation":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/action/citation_signature","submit_replication":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/action/replication_record"}},"created_at":"2026-05-17T23:59:12.335146+00:00","updated_at":"2026-05-17T23:59:12.335146+00:00"}