{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7SVZT6I7NMFN7GAYHUUUNWARZQ","short_pith_number":"pith:7SVZT6I7","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"},"canonical_sha256":"fcab99f91f6b0adf98183d2946d811cc0c4cfa03d118b73fcdfa1a014219139e","source":{"kind":"arxiv","id":"1812.01488","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.01488","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"1812.01488v1","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01488","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"7SVZT6I7NMFN","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7SVZT6I7NMFN7GAY","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7SVZT6I7","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7SVZT6I7NMFN7GAYHUUUNWARZQ","target":"record","payload":{"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"},"canonical_sha256":"fcab99f91f6b0adf98183d2946d811cc0c4cfa03d118b73fcdfa1a014219139e","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"},"source_kind":"arxiv","source_id":"1812.01488","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qqjjamHpUZqJ7X0raRSachuLnd2J2FIt/NCcvIuGHmeJMvJUQFiBL1T+FTKf933guk6U9ct8J/glSkmw7kzDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:21:01.671244Z"},"content_sha256":"d666c683fdfb350fe1d623dd4710cb0c77f9dfb117d3ffba52cf4b558b8fdfec","schema_version":"1.0","event_id":"sha256:d666c683fdfb350fe1d623dd4710cb0c77f9dfb117d3ffba52cf4b558b8fdfec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7SVZT6I7NMFN7GAYHUUUNWARZQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oeWf1VVOQp/Nt0YKcGOFwn5EqGyLW6Pk4V3yn5mZK+dFREIMpwQLk0Z3i+X0D/RqcUFWLQ6JOHjwpc+IBbaqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:21:01.671614Z"},"content_sha256":"d53fa69ff6ee2b29059a6cc10b0aedbc85c012d87a0836cc86bd335fd9bee5c8","schema_version":"1.0","event_id":"sha256:d53fa69ff6ee2b29059a6cc10b0aedbc85c012d87a0836cc86bd335fd9bee5c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/bundle.json","state_url":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-06T19:21:01Z","links":{"resolver":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ","bundle":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/bundle.json","state":"https://pith.science/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7SVZT6I7NMFN7GAYHUUUNWARZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7SVZT6I7NMFN7GAYHUUUNWARZQ","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":"ffa0241c727cda61d3a5263a7fc36b0ec3ec6a6292402abd378de3c234c3b56d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:33:26Z","title_canon_sha256":"217aef5f7b16ec8c9fd6b36a9cbbca8276f570047d6ebb9921e9638622efa386"},"schema_version":"1.0","source":{"id":"1812.01488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.01488","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"1812.01488v1","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01488","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"7SVZT6I7NMFN","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7SVZT6I7NMFN7GAY","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7SVZT6I7","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:d53fa69ff6ee2b29059a6cc10b0aedbc85c012d87a0836cc86bd335fd9bee5c8","target":"graph","created_at":"2026-05-17T23:59:12Z","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"},"paper":{"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","authors_text":"Philip S. Thomas, Saket Tiwari","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:33:26Z","title":"Natural Option Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01488","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:d666c683fdfb350fe1d623dd4710cb0c77f9dfb117d3ffba52cf4b558b8fdfec","target":"record","created_at":"2026-05-17T23:59:12Z","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":"ffa0241c727cda61d3a5263a7fc36b0ec3ec6a6292402abd378de3c234c3b56d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:33:26Z","title_canon_sha256":"217aef5f7b16ec8c9fd6b36a9cbbca8276f570047d6ebb9921e9638622efa386"},"schema_version":"1.0","source":{"id":"1812.01488","kind":"arxiv","version":1}},"canonical_sha256":"fcab99f91f6b0adf98183d2946d811cc0c4cfa03d118b73fcdfa1a014219139e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcab99f91f6b0adf98183d2946d811cc0c4cfa03d118b73fcdfa1a014219139e","first_computed_at":"2026-05-17T23:59:12.335063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:12.335063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H+RI7sVX2zCk8uNIyVKr7sgndDoW5po51d35bROHLa9K75h9Y05HQ5kna/KoDYDwBVT5WtKhY8TBNtvwIcsWDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:12.335574Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.01488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d666c683fdfb350fe1d623dd4710cb0c77f9dfb117d3ffba52cf4b558b8fdfec","sha256:d53fa69ff6ee2b29059a6cc10b0aedbc85c012d87a0836cc86bd335fd9bee5c8"],"state_sha256":"958799b8f7a74aa0062b0c96c763564bf0f39c27a4562aa120424bc90e4bea1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N2pUokoecezj8dSk0E65QNFUVyMNO9jPqfpWWoUekSGst12naYlXsALiMGtZfgetr+fMPYy16l1N/5fh+OpdAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T19:21:01.673686Z","bundle_sha256":"8dba24753f9d798f7941aa53bfbc89775c596094d45de97d993b0d12580aedce"}}