{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NJVKLRM4JLMF7RE4GT3ZV3LACL","short_pith_number":"pith:NJVKLRM4","schema_version":"1.0","canonical_sha256":"6a6aa5c59c4ad85fc49c34f79aed6012e5f1aa910c3ebf84a28cd01cc35bff27","source":{"kind":"arxiv","id":"2007.06482","version":1},"attestation_state":"computed","paper":{"title":"Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Lazaric, Marc Abeille","submitted_at":"2020-07-13T16:30:47Z","abstract_excerpt":"We study the exploration-exploitation dilemma in the linear quadratic regulator (LQR) setting. Inspired by the extended value iteration algorithm used in optimistic algorithms for finite MDPs, we propose to relax the optimistic optimization of \\ofulq and cast it into a constrained \\textit{extended} LQR problem, where an additional control variable implicitly selects the system dynamics within a confidence interval. We then move to the corresponding Lagrangian formulation for which we prove strong duality. As a result, we show that an $\\epsilon$-optimistic controller can be computed efficiently"},"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":"2007.06482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-13T16:30:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7651a7fbfa5e4985f26a4eece4ecd9a5b0f8172c2ebb78f642cd7be14f6666cd","abstract_canon_sha256":"d0aabfa5bb797b1da5a771aa522aafa72a8d489d0b97653efc388ac8855b3994"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:13.229419Z","signature_b64":"uNbiJ0a19jfmQLMHXS2gUg4R1ckVqqWhzqpx30HPnmNK7Rt77E1Blat5XDjGIcy4C8BSl/Ew9zg7Dq5QpylUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a6aa5c59c4ad85fc49c34f79aed6012e5f1aa910c3ebf84a28cd01cc35bff27","last_reissued_at":"2026-07-05T01:18:13.229007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:13.229007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Lazaric, Marc Abeille","submitted_at":"2020-07-13T16:30:47Z","abstract_excerpt":"We study the exploration-exploitation dilemma in the linear quadratic regulator (LQR) setting. Inspired by the extended value iteration algorithm used in optimistic algorithms for finite MDPs, we propose to relax the optimistic optimization of \\ofulq and cast it into a constrained \\textit{extended} LQR problem, where an additional control variable implicitly selects the system dynamics within a confidence interval. We then move to the corresponding Lagrangian formulation for which we prove strong duality. As a result, we show that an $\\epsilon$-optimistic controller can be computed efficiently"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06482","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.06482/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2007.06482","created_at":"2026-07-05T01:18:13.229069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.06482v1","created_at":"2026-07-05T01:18:13.229069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06482","created_at":"2026-07-05T01:18:13.229069+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJVKLRM4JLMF","created_at":"2026-07-05T01:18:13.229069+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJVKLRM4JLMF7RE4","created_at":"2026-07-05T01:18:13.229069+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJVKLRM4","created_at":"2026-07-05T01:18:13.229069+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/NJVKLRM4JLMF7RE4GT3ZV3LACL","json":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL.json","graph_json":"https://pith.science/api/pith-number/NJVKLRM4JLMF7RE4GT3ZV3LACL/graph.json","events_json":"https://pith.science/api/pith-number/NJVKLRM4JLMF7RE4GT3ZV3LACL/events.json","paper":"https://pith.science/paper/NJVKLRM4"},"agent_actions":{"view_html":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL","download_json":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL.json","view_paper":"https://pith.science/paper/NJVKLRM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.06482&json=true","fetch_graph":"https://pith.science/api/pith-number/NJVKLRM4JLMF7RE4GT3ZV3LACL/graph.json","fetch_events":"https://pith.science/api/pith-number/NJVKLRM4JLMF7RE4GT3ZV3LACL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/action/storage_attestation","attest_author":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/action/author_attestation","sign_citation":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/action/citation_signature","submit_replication":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/action/replication_record"}},"created_at":"2026-07-05T01:18:13.229069+00:00","updated_at":"2026-07-05T01:18:13.229069+00:00"}