{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NJVKLRM4JLMF7RE4GT3ZV3LACL","short_pith_number":"pith:NJVKLRM4","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"},"canonical_sha256":"6a6aa5c59c4ad85fc49c34f79aed6012e5f1aa910c3ebf84a28cd01cc35bff27","source":{"kind":"arxiv","id":"2007.06482","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.06482","created_at":"2026-07-05T01:18:13Z"},{"alias_kind":"arxiv_version","alias_value":"2007.06482v1","created_at":"2026-07-05T01:18:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06482","created_at":"2026-07-05T01:18:13Z"},{"alias_kind":"pith_short_12","alias_value":"NJVKLRM4JLMF","created_at":"2026-07-05T01:18:13Z"},{"alias_kind":"pith_short_16","alias_value":"NJVKLRM4JLMF7RE4","created_at":"2026-07-05T01:18:13Z"},{"alias_kind":"pith_short_8","alias_value":"NJVKLRM4","created_at":"2026-07-05T01:18:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NJVKLRM4JLMF7RE4GT3ZV3LACL","target":"record","payload":{"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"},"canonical_sha256":"6a6aa5c59c4ad85fc49c34f79aed6012e5f1aa910c3ebf84a28cd01cc35bff27","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"},"source_kind":"arxiv","source_id":"2007.06482","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:18:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JhkJw2E84ujOAZwXfpct1U/RUhAXy5nuBR6yoAQD65ysR0acfXfccP7Ux2rD6JDf9FtSsutlrBc8D3M8wMmlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:34:49.732267Z"},"content_sha256":"382428851fa5caecdd46a1064cc11d33fe267b602e71aff6a617b5094ba44d92","schema_version":"1.0","event_id":"sha256:382428851fa5caecdd46a1064cc11d33fe267b602e71aff6a617b5094ba44d92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NJVKLRM4JLMF7RE4GT3ZV3LACL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:18:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DVKhtj7LjwRO1ovrgI1KOqd040lObxNHGKGZfhwKIIiZ5TDdBFbn3zSyu0gyCHuw2SOJgO1JIwK3eAUcCHQlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:34:49.732918Z"},"content_sha256":"376c1bab6d3485f4b70001d87c2856943231d5bf8674f3249a34ad4cd9fe185e","schema_version":"1.0","event_id":"sha256:376c1bab6d3485f4b70001d87c2856943231d5bf8674f3249a34ad4cd9fe185e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/bundle.json","state_url":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T06:34:49Z","links":{"resolver":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL","bundle":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/bundle.json","state":"https://pith.science/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJVKLRM4JLMF7RE4GT3ZV3LACL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NJVKLRM4JLMF7RE4GT3ZV3LACL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d0aabfa5bb797b1da5a771aa522aafa72a8d489d0b97653efc388ac8855b3994","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-13T16:30:47Z","title_canon_sha256":"7651a7fbfa5e4985f26a4eece4ecd9a5b0f8172c2ebb78f642cd7be14f6666cd"},"schema_version":"1.0","source":{"id":"2007.06482","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.06482","created_at":"2026-07-05T01:18:13Z"},{"alias_kind":"arxiv_version","alias_value":"2007.06482v1","created_at":"2026-07-05T01:18:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06482","created_at":"2026-07-05T01:18:13Z"},{"alias_kind":"pith_short_12","alias_value":"NJVKLRM4JLMF","created_at":"2026-07-05T01:18:13Z"},{"alias_kind":"pith_short_16","alias_value":"NJVKLRM4JLMF7RE4","created_at":"2026-07-05T01:18:13Z"},{"alias_kind":"pith_short_8","alias_value":"NJVKLRM4","created_at":"2026-07-05T01:18:13Z"}],"graph_snapshots":[{"event_id":"sha256:376c1bab6d3485f4b70001d87c2856943231d5bf8674f3249a34ad4cd9fe185e","target":"graph","created_at":"2026-07-05T01:18:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.06482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alessandro Lazaric, Marc Abeille","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-13T16:30:47Z","title":"Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06482","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:382428851fa5caecdd46a1064cc11d33fe267b602e71aff6a617b5094ba44d92","target":"record","created_at":"2026-07-05T01:18:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d0aabfa5bb797b1da5a771aa522aafa72a8d489d0b97653efc388ac8855b3994","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-13T16:30:47Z","title_canon_sha256":"7651a7fbfa5e4985f26a4eece4ecd9a5b0f8172c2ebb78f642cd7be14f6666cd"},"schema_version":"1.0","source":{"id":"2007.06482","kind":"arxiv","version":1}},"canonical_sha256":"6a6aa5c59c4ad85fc49c34f79aed6012e5f1aa910c3ebf84a28cd01cc35bff27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a6aa5c59c4ad85fc49c34f79aed6012e5f1aa910c3ebf84a28cd01cc35bff27","first_computed_at":"2026-07-05T01:18:13.229007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:18:13.229007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uNbiJ0a19jfmQLMHXS2gUg4R1ckVqqWhzqpx30HPnmNK7Rt77E1Blat5XDjGIcy4C8BSl/Ew9zg7Dq5QpylUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:18:13.229419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.06482","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:382428851fa5caecdd46a1064cc11d33fe267b602e71aff6a617b5094ba44d92","sha256:376c1bab6d3485f4b70001d87c2856943231d5bf8674f3249a34ad4cd9fe185e"],"state_sha256":"dc7254e673e09bdefc56a1f3247273addd3a85ba1d18e03c80bf0f300131537f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+FP9t41+lQ8ElcfDroI2UpzjhpvguYBrGVbkV1cH1DrtlWJd/DIlw3JvvKSoH7RetBWaEHFOtpUJ9cfRreDzCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:34:49.736080Z","bundle_sha256":"9746ff599d2186ba8bca0a0af2e90c3d5fb8bdd93d1528355b95abf26bd2a08b"}}