{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ELTBHBPZ3EHPX5CWMUHOVDWE3F","short_pith_number":"pith:ELTBHBPZ","canonical_record":{"source":{"id":"2112.03097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T15:07:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d19365a30fc4fdf2ba3c210758d843c673cbcb4b75f047dc781ebe24e1c0fd3","abstract_canon_sha256":"a83bba8629ef6bc12b3fc31e464c5c7fab52ee73af8951f23985e5e8f3f9a54c"},"schema_version":"1.0"},"canonical_sha256":"22e61385f9d90efbf456650eea8ec4d95d3e31f5f1de03fa6cbe63450e0cee99","source":{"kind":"arxiv","id":"2112.03097","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03097","created_at":"2026-07-05T03:38:01Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03097v1","created_at":"2026-07-05T03:38:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03097","created_at":"2026-07-05T03:38:01Z"},{"alias_kind":"pith_short_12","alias_value":"ELTBHBPZ3EHP","created_at":"2026-07-05T03:38:01Z"},{"alias_kind":"pith_short_16","alias_value":"ELTBHBPZ3EHPX5CW","created_at":"2026-07-05T03:38:01Z"},{"alias_kind":"pith_short_8","alias_value":"ELTBHBPZ","created_at":"2026-07-05T03:38:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ELTBHBPZ3EHPX5CWMUHOVDWE3F","target":"record","payload":{"canonical_record":{"source":{"id":"2112.03097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T15:07:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d19365a30fc4fdf2ba3c210758d843c673cbcb4b75f047dc781ebe24e1c0fd3","abstract_canon_sha256":"a83bba8629ef6bc12b3fc31e464c5c7fab52ee73af8951f23985e5e8f3f9a54c"},"schema_version":"1.0"},"canonical_sha256":"22e61385f9d90efbf456650eea8ec4d95d3e31f5f1de03fa6cbe63450e0cee99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:01.915980Z","signature_b64":"Idf6ocsMXCby51eqEUL1m+sRMCkqB8PCJH4drJFK+HbCuVq+ELu+fITfEbwiRVbuMyZoqXL7jUeSaZ7wqYX0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22e61385f9d90efbf456650eea8ec4d95d3e31f5f1de03fa6cbe63450e0cee99","last_reissued_at":"2026-07-05T03:38:01.915441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:01.915441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.03097","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":"2026-07-05T03:38:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KhD+AvY+ZBzBZMwy6PcwoRnyYA1EEuSzNTVRuGOgV+Kq/vACAV18Gw/ZVZwWmC7017znUB8CQOi4VBY2oGKQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:46:46.858051Z"},"content_sha256":"e476ae8ba226a76c747004bae346a54de2c3e9e287cd4088fee18edf72409097","schema_version":"1.0","event_id":"sha256:e476ae8ba226a76c747004bae346a54de2c3e9e287cd4088fee18edf72409097"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ELTBHBPZ3EHPX5CWMUHOVDWE3F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flexible Option Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Martin Klissarov","submitted_at":"2021-12-06T15:07:48Z","abstract_excerpt":"Temporal abstraction in reinforcement learning (RL), offers the promise of improving generalization and knowledge transfer in complex environments, by propagating information more efficiently over time. Although option learning was initially formulated in a way that allows updating many options simultaneously, using off-policy, intra-option learning (Sutton, Precup & Singh, 1999), many of the recent hierarchical reinforcement learning approaches only update a single option at a time: the option currently executing. We revisit and extend intra-option learning in the context of deep reinforcemen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03097","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/2112.03097/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:38:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z3vppROF6oT0rCO4SOWLpH1VX/f5T0KvC9uNVlWXiVW3CCgIXOUBTAzTLwuj+M+CT9RwFTVRlISrBrIIub9dCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:46:46.858560Z"},"content_sha256":"b924e57aac4f8c5708421f75d7d0d35e31f706b4bf414cffc6d17e9107191aae","schema_version":"1.0","event_id":"sha256:b924e57aac4f8c5708421f75d7d0d35e31f706b4bf414cffc6d17e9107191aae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ELTBHBPZ3EHPX5CWMUHOVDWE3F/bundle.json","state_url":"https://pith.science/pith/ELTBHBPZ3EHPX5CWMUHOVDWE3F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ELTBHBPZ3EHPX5CWMUHOVDWE3F/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":"2026-08-06T08:46:46Z","links":{"resolver":"https://pith.science/pith/ELTBHBPZ3EHPX5CWMUHOVDWE3F","bundle":"https://pith.science/pith/ELTBHBPZ3EHPX5CWMUHOVDWE3F/bundle.json","state":"https://pith.science/pith/ELTBHBPZ3EHPX5CWMUHOVDWE3F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ELTBHBPZ3EHPX5CWMUHOVDWE3F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ELTBHBPZ3EHPX5CWMUHOVDWE3F","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":"a83bba8629ef6bc12b3fc31e464c5c7fab52ee73af8951f23985e5e8f3f9a54c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T15:07:48Z","title_canon_sha256":"7d19365a30fc4fdf2ba3c210758d843c673cbcb4b75f047dc781ebe24e1c0fd3"},"schema_version":"1.0","source":{"id":"2112.03097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03097","created_at":"2026-07-05T03:38:01Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03097v1","created_at":"2026-07-05T03:38:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03097","created_at":"2026-07-05T03:38:01Z"},{"alias_kind":"pith_short_12","alias_value":"ELTBHBPZ3EHP","created_at":"2026-07-05T03:38:01Z"},{"alias_kind":"pith_short_16","alias_value":"ELTBHBPZ3EHPX5CW","created_at":"2026-07-05T03:38:01Z"},{"alias_kind":"pith_short_8","alias_value":"ELTBHBPZ","created_at":"2026-07-05T03:38:01Z"}],"graph_snapshots":[{"event_id":"sha256:b924e57aac4f8c5708421f75d7d0d35e31f706b4bf414cffc6d17e9107191aae","target":"graph","created_at":"2026-07-05T03:38:01Z","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/2112.03097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Temporal abstraction in reinforcement learning (RL), offers the promise of improving generalization and knowledge transfer in complex environments, by propagating information more efficiently over time. Although option learning was initially formulated in a way that allows updating many options simultaneously, using off-policy, intra-option learning (Sutton, Precup & Singh, 1999), many of the recent hierarchical reinforcement learning approaches only update a single option at a time: the option currently executing. We revisit and extend intra-option learning in the context of deep reinforcemen","authors_text":"Doina Precup, Martin Klissarov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T15:07:48Z","title":"Flexible Option Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03097","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:e476ae8ba226a76c747004bae346a54de2c3e9e287cd4088fee18edf72409097","target":"record","created_at":"2026-07-05T03:38:01Z","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":"a83bba8629ef6bc12b3fc31e464c5c7fab52ee73af8951f23985e5e8f3f9a54c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T15:07:48Z","title_canon_sha256":"7d19365a30fc4fdf2ba3c210758d843c673cbcb4b75f047dc781ebe24e1c0fd3"},"schema_version":"1.0","source":{"id":"2112.03097","kind":"arxiv","version":1}},"canonical_sha256":"22e61385f9d90efbf456650eea8ec4d95d3e31f5f1de03fa6cbe63450e0cee99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22e61385f9d90efbf456650eea8ec4d95d3e31f5f1de03fa6cbe63450e0cee99","first_computed_at":"2026-07-05T03:38:01.915441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:38:01.915441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Idf6ocsMXCby51eqEUL1m+sRMCkqB8PCJH4drJFK+HbCuVq+ELu+fITfEbwiRVbuMyZoqXL7jUeSaZ7wqYX0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:38:01.915980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.03097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e476ae8ba226a76c747004bae346a54de2c3e9e287cd4088fee18edf72409097","sha256:b924e57aac4f8c5708421f75d7d0d35e31f706b4bf414cffc6d17e9107191aae"],"state_sha256":"01ccd3166e0ba43c81cefb68a719c626632deec1ca59db9d152289b5a1d95e54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P6Qn29ARNQ3YijyXBGii+/7XYCo4dbPnh9sKzkgidMYWY8O3x7vSfSEnAPob5xMSUzsXEYkuQRFv53EzGVSqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:46:46.864246Z","bundle_sha256":"823438ee8be3e1386cc6f7a578f1c63c5aa7dc9c6511cfefef0c9cb4037ad232"}}