{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WZHJJWGCDZ7Q2EWSZ7JDAKS3TS","short_pith_number":"pith:WZHJJWGC","schema_version":"1.0","canonical_sha256":"b64e94d8c21e7f0d12d2cfd2302a5b9ca1a9485ae3268afba5ec639d313f9986","source":{"kind":"arxiv","id":"1903.05803","version":2},"attestation_state":"computed","paper":{"title":"On Applications of Bootstrap in Continuous Space Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ambuj Tewari, George Michailidis, Mohamad Kazem Shirani Faradonbeh","submitted_at":"2019-03-14T03:37:49Z","abstract_excerpt":"In decision making problems for continuous state and action spaces, linear dynamical models are widely employed. Specifically, policies for stochastic linear systems subject to quadratic cost functions capture a large number of applications in reinforcement learning. Selected randomized policies have been studied in the literature recently that address the trade-off between identification and control. However, little is known about policies based on bootstrapping observed states and actions. In this work, we show that bootstrap-based policies achieve a square root scaling of regret with respec"},"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":"1903.05803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T03:37:49Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"db9f93250acd8095451b670f7d78b4ebc9d07c794be2dcc8c9d017d9a8794e45","abstract_canon_sha256":"b1ce03a444e90db54db74b819ed403c7405478a60ba7c8c704212ac85252ae7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:04.478368Z","signature_b64":"NQmRwbAVnvRYwmUrKQnsclEzO5PmzEcJBCMi3fGxEExSlO9EvNGPfUrFXrjpIIg1BeCoECusE1U8AR6sF4maAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b64e94d8c21e7f0d12d2cfd2302a5b9ca1a9485ae3268afba5ec639d313f9986","last_reissued_at":"2026-05-17T23:48:04.477965Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:04.477965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Applications of Bootstrap in Continuous Space Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ambuj Tewari, George Michailidis, Mohamad Kazem Shirani Faradonbeh","submitted_at":"2019-03-14T03:37:49Z","abstract_excerpt":"In decision making problems for continuous state and action spaces, linear dynamical models are widely employed. Specifically, policies for stochastic linear systems subject to quadratic cost functions capture a large number of applications in reinforcement learning. Selected randomized policies have been studied in the literature recently that address the trade-off between identification and control. However, little is known about policies based on bootstrapping observed states and actions. In this work, we show that bootstrap-based policies achieve a square root scaling of regret with respec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05803","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":"1903.05803","created_at":"2026-05-17T23:48:04.478021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.05803v2","created_at":"2026-05-17T23:48:04.478021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05803","created_at":"2026-05-17T23:48:04.478021+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZHJJWGCDZ7Q","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZHJJWGCDZ7Q2EWS","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZHJJWGC","created_at":"2026-05-18T12:33:33.725879+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/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS","json":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS.json","graph_json":"https://pith.science/api/pith-number/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/graph.json","events_json":"https://pith.science/api/pith-number/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/events.json","paper":"https://pith.science/paper/WZHJJWGC"},"agent_actions":{"view_html":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS","download_json":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS.json","view_paper":"https://pith.science/paper/WZHJJWGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.05803&json=true","fetch_graph":"https://pith.science/api/pith-number/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/graph.json","fetch_events":"https://pith.science/api/pith-number/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/action/storage_attestation","attest_author":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/action/author_attestation","sign_citation":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/action/citation_signature","submit_replication":"https://pith.science/pith/WZHJJWGCDZ7Q2EWSZ7JDAKS3TS/action/replication_record"}},"created_at":"2026-05-17T23:48:04.478021+00:00","updated_at":"2026-05-17T23:48:04.478021+00:00"}