{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IGBK7G4JMNHIAQJ4BBVXQ5R6JF","short_pith_number":"pith:IGBK7G4J","schema_version":"1.0","canonical_sha256":"4182af9b89634e80413c086b78763e4973d8e059346207254c8242a6bdfc8c9e","source":{"kind":"arxiv","id":"1802.09646","version":1},"attestation_state":"computed","paper":{"title":"Optimizing over a Restricted Policy Class in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ershad Banijamali, Mohammad Ghavamzadeh, Nikos Vlassis, Yasin Abbasi-Yadkori","submitted_at":"2018-02-26T23:51:57Z","abstract_excerpt":"We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem is of great interest in applications in which a number of reasonably good (or safe) policies are already known and we are only interested in optimizing in their convex hull. We show that this problem is NP-hard to solve exactly as well as to approximate to arbitrary accuracy. However, under a condition that is akin to the occupancy measures of the base policies having large overlap, we show that there exists an effic"},"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":"1802.09646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T23:51:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3f2140084943a2445a66163cdd3e943197f4c4064b7c4d19af6c353b810d6369","abstract_canon_sha256":"a8135576c14eee229d0e5c46c76de67a0463c3a85aad6411f911095723810d07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:30.530926Z","signature_b64":"ZGoFz6ZIfpYLVBwHEQHrLiOkPrG+gomq/HknKImwRQuvLQg0QdOpq7P3D2uFxNeMjgfSNemn3eDiTfJUrMIYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4182af9b89634e80413c086b78763e4973d8e059346207254c8242a6bdfc8c9e","last_reissued_at":"2026-05-18T00:22:30.530175Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:30.530175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing over a Restricted Policy Class in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ershad Banijamali, Mohammad Ghavamzadeh, Nikos Vlassis, Yasin Abbasi-Yadkori","submitted_at":"2018-02-26T23:51:57Z","abstract_excerpt":"We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem is of great interest in applications in which a number of reasonably good (or safe) policies are already known and we are only interested in optimizing in their convex hull. We show that this problem is NP-hard to solve exactly as well as to approximate to arbitrary accuracy. However, under a condition that is akin to the occupancy measures of the base policies having large overlap, we show that there exists an effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09646","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":"1802.09646","created_at":"2026-05-18T00:22:30.530295+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.09646v1","created_at":"2026-05-18T00:22:30.530295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09646","created_at":"2026-05-18T00:22:30.530295+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGBK7G4JMNHI","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGBK7G4JMNHIAQJ4","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGBK7G4J","created_at":"2026-05-18T12:32:28.185984+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/IGBK7G4JMNHIAQJ4BBVXQ5R6JF","json":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF.json","graph_json":"https://pith.science/api/pith-number/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/graph.json","events_json":"https://pith.science/api/pith-number/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/events.json","paper":"https://pith.science/paper/IGBK7G4J"},"agent_actions":{"view_html":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF","download_json":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF.json","view_paper":"https://pith.science/paper/IGBK7G4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.09646&json=true","fetch_graph":"https://pith.science/api/pith-number/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/graph.json","fetch_events":"https://pith.science/api/pith-number/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/action/storage_attestation","attest_author":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/action/author_attestation","sign_citation":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/action/citation_signature","submit_replication":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/action/replication_record"}},"created_at":"2026-05-18T00:22:30.530295+00:00","updated_at":"2026-05-18T00:22:30.530295+00:00"}