{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GQYIXHLU6672MNQWL4SXWABFM2","short_pith_number":"pith:GQYIXHLU","schema_version":"1.0","canonical_sha256":"34308b9d74f7bfa636165f257b002566b551f83a53eb0de029437e3e2de4047b","source":{"kind":"arxiv","id":"1610.02847","version":1},"attestation_state":"computed","paper":{"title":"Situational Awareness by Risk-Conscious Skills","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":"2016-10-10T11:01:32Z","abstract_excerpt":"Hierarchical Reinforcement Learning has been previously shown to speed up the convergence rate of RL planning algorithms as well as mitigate feature-based model misspecification (Mankowitz et. al. 2016a,b, Bacon 2015). To do so, it utilizes hierarchical abstractions, also known as skills -- a type of temporally extended action (Sutton et. al. 1999) to plan at a higher level, abstracting away from the lower-level details. We incorporate risk sensitivity, also referred to as Situational Awareness (SA), into hierarchical RL for the first time by defining and learning risk aware skills in a Probab"},"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":"1610.02847","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-10T11:01:32Z","cross_cats_sorted":[],"title_canon_sha256":"95e6aa29adabc78670bae3603730e4c54c7cb1eb914a2d641c02ca2445abf7e1","abstract_canon_sha256":"e9eee182e028686db8f0c811a4a8fd4f432b46a4ab63dac5494d28fb7e43633f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:50.576970Z","signature_b64":"FTk12emAY3lhFuih6/aNL63t4ZDA0Tn/zjMG4EQJTF76Wxji1HHuhHSGLDm7ZnvXpgcbJAFGYwOlyP9KwgC/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34308b9d74f7bfa636165f257b002566b551f83a53eb0de029437e3e2de4047b","last_reissued_at":"2026-05-18T01:02:50.576444Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:50.576444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Situational Awareness by Risk-Conscious Skills","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":"2016-10-10T11:01:32Z","abstract_excerpt":"Hierarchical Reinforcement Learning has been previously shown to speed up the convergence rate of RL planning algorithms as well as mitigate feature-based model misspecification (Mankowitz et. al. 2016a,b, Bacon 2015). To do so, it utilizes hierarchical abstractions, also known as skills -- a type of temporally extended action (Sutton et. al. 1999) to plan at a higher level, abstracting away from the lower-level details. We incorporate risk sensitivity, also referred to as Situational Awareness (SA), into hierarchical RL for the first time by defining and learning risk aware skills in a Probab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.02847","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":"1610.02847","created_at":"2026-05-18T01:02:50.576521+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.02847v1","created_at":"2026-05-18T01:02:50.576521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.02847","created_at":"2026-05-18T01:02:50.576521+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQYIXHLU6672","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQYIXHLU6672MNQW","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQYIXHLU","created_at":"2026-05-18T12:30:19.053100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2408.08812","citing_title":"TRAM: Test-Time Risk Adaptation with Mixture of Agents","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQYIXHLU6672MNQWL4SXWABFM2","json":"https://pith.science/pith/GQYIXHLU6672MNQWL4SXWABFM2.json","graph_json":"https://pith.science/api/pith-number/GQYIXHLU6672MNQWL4SXWABFM2/graph.json","events_json":"https://pith.science/api/pith-number/GQYIXHLU6672MNQWL4SXWABFM2/events.json","paper":"https://pith.science/paper/GQYIXHLU"},"agent_actions":{"view_html":"https://pith.science/pith/GQYIXHLU6672MNQWL4SXWABFM2","download_json":"https://pith.science/pith/GQYIXHLU6672MNQWL4SXWABFM2.json","view_paper":"https://pith.science/paper/GQYIXHLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.02847&json=true","fetch_graph":"https://pith.science/api/pith-number/GQYIXHLU6672MNQWL4SXWABFM2/graph.json","fetch_events":"https://pith.science/api/pith-number/GQYIXHLU6672MNQWL4SXWABFM2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQYIXHLU6672MNQWL4SXWABFM2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQYIXHLU6672MNQWL4SXWABFM2/action/storage_attestation","attest_author":"https://pith.science/pith/GQYIXHLU6672MNQWL4SXWABFM2/action/author_attestation","sign_citation":"https://pith.science/pith/GQYIXHLU6672MNQWL4SXWABFM2/action/citation_signature","submit_replication":"https://pith.science/pith/GQYIXHLU6672MNQWL4SXWABFM2/action/replication_record"}},"created_at":"2026-05-18T01:02:50.576521+00:00","updated_at":"2026-05-18T01:02:50.576521+00:00"}