{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IBO524HPBXFBAXSIOEW2Z2HKTX","short_pith_number":"pith:IBO524HP","schema_version":"1.0","canonical_sha256":"405ddd70ef0dca105e48712dace8ea9ddb01e073817817356a89aee57b3cf862","source":{"kind":"arxiv","id":"1711.07832","version":1},"attestation_state":"computed","paper":{"title":"Situationally Aware Options","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aviv Tamar, Daniel J. Mankowitz, Shie Mannor","submitted_at":"2017-11-20T08:11:12Z","abstract_excerpt":"Hierarchical abstractions, also known as options -- a type of temporally extended action (Sutton et. al. 1999) that enables a reinforcement learning agent to plan at a higher level, abstracting away from the lower-level details. In this work, we learn reusable options whose parameters can vary, encouraging different behaviors, based on the current situation. In principle, these behaviors can include vigor, defence or even risk-averseness. These are some examples of what we refer to in the broader context as Situational Awareness (SA). We incorporate SA, in the form of vigor, into hierarchical "},"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":"1711.07832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-20T08:11:12Z","cross_cats_sorted":[],"title_canon_sha256":"83b9ee596642377b6ec0df216d30fcc22129c4d7c5a49a37719b3634391948ea","abstract_canon_sha256":"4f95fa95c0bf4bb1672ea7d7762c5a5b1ee786e743cc7e3e515433745e5208fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:56.403422Z","signature_b64":"7Y22jNNKx4obRnPCzW0rN5P/vBBJs6CHdcZb7XnpzPYLtB8kTN5HYc+PSp3uYi6DNW3/y3SrJDcmJ46d6OxSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"405ddd70ef0dca105e48712dace8ea9ddb01e073817817356a89aee57b3cf862","last_reissued_at":"2026-05-18T00:29:56.403018Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:56.403018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Situationally Aware Options","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aviv Tamar, Daniel J. Mankowitz, Shie Mannor","submitted_at":"2017-11-20T08:11:12Z","abstract_excerpt":"Hierarchical abstractions, also known as options -- a type of temporally extended action (Sutton et. al. 1999) that enables a reinforcement learning agent to plan at a higher level, abstracting away from the lower-level details. In this work, we learn reusable options whose parameters can vary, encouraging different behaviors, based on the current situation. In principle, these behaviors can include vigor, defence or even risk-averseness. These are some examples of what we refer to in the broader context as Situational Awareness (SA). We incorporate SA, in the form of vigor, into hierarchical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07832","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":"1711.07832","created_at":"2026-05-18T00:29:56.403079+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.07832v1","created_at":"2026-05-18T00:29:56.403079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07832","created_at":"2026-05-18T00:29:56.403079+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBO524HPBXFB","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBO524HPBXFBAXSI","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBO524HP","created_at":"2026-05-18T12:31:21.493067+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/IBO524HPBXFBAXSIOEW2Z2HKTX","json":"https://pith.science/pith/IBO524HPBXFBAXSIOEW2Z2HKTX.json","graph_json":"https://pith.science/api/pith-number/IBO524HPBXFBAXSIOEW2Z2HKTX/graph.json","events_json":"https://pith.science/api/pith-number/IBO524HPBXFBAXSIOEW2Z2HKTX/events.json","paper":"https://pith.science/paper/IBO524HP"},"agent_actions":{"view_html":"https://pith.science/pith/IBO524HPBXFBAXSIOEW2Z2HKTX","download_json":"https://pith.science/pith/IBO524HPBXFBAXSIOEW2Z2HKTX.json","view_paper":"https://pith.science/paper/IBO524HP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.07832&json=true","fetch_graph":"https://pith.science/api/pith-number/IBO524HPBXFBAXSIOEW2Z2HKTX/graph.json","fetch_events":"https://pith.science/api/pith-number/IBO524HPBXFBAXSIOEW2Z2HKTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBO524HPBXFBAXSIOEW2Z2HKTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBO524HPBXFBAXSIOEW2Z2HKTX/action/storage_attestation","attest_author":"https://pith.science/pith/IBO524HPBXFBAXSIOEW2Z2HKTX/action/author_attestation","sign_citation":"https://pith.science/pith/IBO524HPBXFBAXSIOEW2Z2HKTX/action/citation_signature","submit_replication":"https://pith.science/pith/IBO524HPBXFBAXSIOEW2Z2HKTX/action/replication_record"}},"created_at":"2026-05-18T00:29:56.403079+00:00","updated_at":"2026-05-18T00:29:56.403079+00:00"}