{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:46T62LQDKOFOVPD5ITCON7NTUY","short_pith_number":"pith:46T62LQD","schema_version":"1.0","canonical_sha256":"e7a7ed2e03538aeabc7d44c4e6fdb3a61eb7783ab7bff7810f967e7cf3b6606e","source":{"kind":"arxiv","id":"1602.06346","version":2},"attestation_state":"computed","paper":{"title":"Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernardo \\'Avila Pires, Csaba Szepesv\\'ari","submitted_at":"2016-02-19T23:46:11Z","abstract_excerpt":"In this paper we study a model-based approach to calculating approximately optimal policies in Markovian Decision Processes. In particular, we derive novel bounds on the loss of using a policy derived from a factored linear model, a class of models which generalize numerous previous models out of those that come with strong computational guarantees. For the first time in the literature, we derive performance bounds for model-based techniques where the model inaccuracy is measured in weighted norms. Moreover, our bounds show a decreased sensitivity to the discount factor and, unlike similar bou"},"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":"1602.06346","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-19T23:46:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e5720cdc47b9e67281bf8d824e05531b7c3b9d64e3db30bf31470e95d4cebfd7","abstract_canon_sha256":"34b4ac6d2f10b9b87b2c26997fb1f7b4228ec35ec008be6a3bf3a9704e2e2425"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:09.213546Z","signature_b64":"gm1DAJw1CDxYW5Rx95MVLo2Mrpz1GAZRFvHSfo9b8ZPmy5KorZvAJDKCH2rs6h4DLUfO4Tp1SJRC8auoWgmZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7a7ed2e03538aeabc7d44c4e6fdb3a61eb7783ab7bff7810f967e7cf3b6606e","last_reissued_at":"2026-05-18T01:04:09.213036Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:09.213036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernardo \\'Avila Pires, Csaba Szepesv\\'ari","submitted_at":"2016-02-19T23:46:11Z","abstract_excerpt":"In this paper we study a model-based approach to calculating approximately optimal policies in Markovian Decision Processes. In particular, we derive novel bounds on the loss of using a policy derived from a factored linear model, a class of models which generalize numerous previous models out of those that come with strong computational guarantees. For the first time in the literature, we derive performance bounds for model-based techniques where the model inaccuracy is measured in weighted norms. Moreover, our bounds show a decreased sensitivity to the discount factor and, unlike similar bou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.06346","kind":"arxiv","version":2},"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":"1602.06346","created_at":"2026-05-18T01:04:09.213116+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.06346v2","created_at":"2026-05-18T01:04:09.213116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.06346","created_at":"2026-05-18T01:04:09.213116+00:00"},{"alias_kind":"pith_short_12","alias_value":"46T62LQDKOFO","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"46T62LQDKOFOVPD5","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"46T62LQD","created_at":"2026-05-18T12:29:58.707656+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/46T62LQDKOFOVPD5ITCON7NTUY","json":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY.json","graph_json":"https://pith.science/api/pith-number/46T62LQDKOFOVPD5ITCON7NTUY/graph.json","events_json":"https://pith.science/api/pith-number/46T62LQDKOFOVPD5ITCON7NTUY/events.json","paper":"https://pith.science/paper/46T62LQD"},"agent_actions":{"view_html":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY","download_json":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY.json","view_paper":"https://pith.science/paper/46T62LQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.06346&json=true","fetch_graph":"https://pith.science/api/pith-number/46T62LQDKOFOVPD5ITCON7NTUY/graph.json","fetch_events":"https://pith.science/api/pith-number/46T62LQDKOFOVPD5ITCON7NTUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY/action/storage_attestation","attest_author":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY/action/author_attestation","sign_citation":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY/action/citation_signature","submit_replication":"https://pith.science/pith/46T62LQDKOFOVPD5ITCON7NTUY/action/replication_record"}},"created_at":"2026-05-18T01:04:09.213116+00:00","updated_at":"2026-05-18T01:04:09.213116+00:00"}