{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AUWUUFHQATZIKLBXPEEHG7LSUS","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":"4f897a88d3933f2929803056397eb17b2f7d17cf5baadb965a778d6e17d27cd0","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-02-22T12:16:43Z","title_canon_sha256":"a6f166dddc03cbf7bd148e09cec8ebf319ce7dd373b414427b5c158acb0a85e8"},"schema_version":"1.0","source":{"id":"2402.14483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14483","created_at":"2026-07-05T07:48:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14483v1","created_at":"2026-07-05T07:48:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14483","created_at":"2026-07-05T07:48:11Z"},{"alias_kind":"pith_short_12","alias_value":"AUWUUFHQATZI","created_at":"2026-07-05T07:48:11Z"},{"alias_kind":"pith_short_16","alias_value":"AUWUUFHQATZIKLBX","created_at":"2026-07-05T07:48:11Z"},{"alias_kind":"pith_short_8","alias_value":"AUWUUFHQ","created_at":"2026-07-05T07:48:11Z"}],"graph_snapshots":[{"event_id":"sha256:0869f1cb50cf1103087617b1829761057b59a18250fd1e0e4ac22349621eb61a","target":"graph","created_at":"2026-07-05T07:48:11Z","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/2402.14483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This article introduces a novel framework for data-driven linear quadratic regulator (LQR) design. First, we introduce a reinforcement learning paradigm for on-policy data-driven LQR, where exploration and exploitation are simultaneously performed while guaranteeing robust stability of the whole closed-loop system encompassing the plant and the control/learning dynamics. Then, we propose Model Reference Adaptive Reinforcement Learning (MR-ARL), a control architecture integrating tools from reinforcement learning and model reference adaptive control. The approach stands on a variable reference ","authors_text":"Alessandro Bosso, Giuseppe Notarstefano, Marco Borghesi","cross_cats":["cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-02-22T12:16:43Z","title":"MR-ARL: Model Reference Adaptive Reinforcement Learning for Robustly Stable On-Policy Data-Driven LQR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14483","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":"sha256:10c52755aa41675cc37e64c3b70b3ea9bd066093acabc278f9e6740dacbade78","target":"record","created_at":"2026-07-05T07:48:11Z","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":"4f897a88d3933f2929803056397eb17b2f7d17cf5baadb965a778d6e17d27cd0","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-02-22T12:16:43Z","title_canon_sha256":"a6f166dddc03cbf7bd148e09cec8ebf319ce7dd373b414427b5c158acb0a85e8"},"schema_version":"1.0","source":{"id":"2402.14483","kind":"arxiv","version":1}},"canonical_sha256":"052d4a14f004f2852c377908737d72a4989e44df82ffbec085a5fb71b6b25197","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"052d4a14f004f2852c377908737d72a4989e44df82ffbec085a5fb71b6b25197","first_computed_at":"2026-07-05T07:48:11.034193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:11.034193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ir+aqGTJ6QJKkVwdc5PVK6AztkyWxq4cgPv1cDKofwdLVk9Mfm7wsZsW1WWbyl7Yd7bQg/OnpOLye4AjPrYBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:11.034718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10c52755aa41675cc37e64c3b70b3ea9bd066093acabc278f9e6740dacbade78","sha256:0869f1cb50cf1103087617b1829761057b59a18250fd1e0e4ac22349621eb61a"],"state_sha256":"333b483d83f023ebf4c463a97932117e61b0ba6b96cbb933fcc1ce25cc5d0233"}