{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:G6E5LYFNXM33NSLWXJBYFGJQNJ","short_pith_number":"pith:G6E5LYFN","canonical_record":{"source":{"id":"2011.04970","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-11-10T08:36:31Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"2593cc6fc030120b1f0609a6f7e0da03629111db517e056e678891d71e842dc9","abstract_canon_sha256":"4841a811ff57d950aaa68209e57dac7e9cb09df8dd9a1faeabc9dbfe819812f8"},"schema_version":"1.0"},"canonical_sha256":"3789d5e0adbb37b6c976ba438299306a4be020a704133b4fda54c1b4212a7b98","source":{"kind":"arxiv","id":"2011.04970","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04970","created_at":"2026-07-05T01:50:42Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04970v1","created_at":"2026-07-05T01:50:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04970","created_at":"2026-07-05T01:50:42Z"},{"alias_kind":"pith_short_12","alias_value":"G6E5LYFNXM33","created_at":"2026-07-05T01:50:42Z"},{"alias_kind":"pith_short_16","alias_value":"G6E5LYFNXM33NSLW","created_at":"2026-07-05T01:50:42Z"},{"alias_kind":"pith_short_8","alias_value":"G6E5LYFN","created_at":"2026-07-05T01:50:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:G6E5LYFNXM33NSLWXJBYFGJQNJ","target":"record","payload":{"canonical_record":{"source":{"id":"2011.04970","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-11-10T08:36:31Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"2593cc6fc030120b1f0609a6f7e0da03629111db517e056e678891d71e842dc9","abstract_canon_sha256":"4841a811ff57d950aaa68209e57dac7e9cb09df8dd9a1faeabc9dbfe819812f8"},"schema_version":"1.0"},"canonical_sha256":"3789d5e0adbb37b6c976ba438299306a4be020a704133b4fda54c1b4212a7b98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:42.181544Z","signature_b64":"XKO8mHY62HDixnuEpMsq2VPZgToS12w+MD/NtmB0HiorsuQHpQpstRRppnlgM3icLsZwgfL6/Wo3QaUuPWHjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3789d5e0adbb37b6c976ba438299306a4be020a704133b4fda54c1b4212a7b98","last_reissued_at":"2026-07-05T01:50:42.181119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:42.181119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.04970","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":"2026-07-05T01:50:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e2Z7oI0kpBtka6ooq94PM+G9bkqdpieXOYEJO/Wrwgbe3TeHqVv4vi1TmpsZTA3Pb+Q88NBFQVDkigkhOaszAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:08:28.562926Z"},"content_sha256":"2dd66dd9ff1b757cd3fb55c4f3382ed026b270020bbf70ee9a7ca1bf85499080","schema_version":"1.0","event_id":"sha256:2dd66dd9ff1b757cd3fb55c4f3382ed026b270020bbf70ee9a7ca1bf85499080"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:G6E5LYFNXM33NSLWXJBYFGJQNJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Q-learning algorithm for discrete-time linear-quadratic control with random parameters of unknown distribution: convergence and stabilization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"math.OC","authors_text":"Fu Zhang, Kai Du, Qingxin Meng","submitted_at":"2020-11-10T08:36:31Z","abstract_excerpt":"This paper studies an infinite horizon optimal control problem for discrete-time linear systems and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. A classical approach is to solve an algebraic Riccati equation that involves mathematical expectations and requires certain statistical information of the parameters. In this paper, we propose an online iterative algorithm in the spirit of Q-learning for the situation where only one random sample of parameters emerges at each time step. The first theorem proves the equivalence "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04970","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/2011.04970/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":"2026-07-05T01:50:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Znm+sv5JTdACRWe/NYjSyUm8p/43OkFla0G/FOAr53rxiR3nNQ2+yxZhLmm6T7k4PEy4bL+5VZBtPV/EymjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:08:28.563301Z"},"content_sha256":"6b5dd4e0fbd4294847ca89b3d0e7d36caacc5ce48dcb45c8750e911f5d479bc4","schema_version":"1.0","event_id":"sha256:6b5dd4e0fbd4294847ca89b3d0e7d36caacc5ce48dcb45c8750e911f5d479bc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G6E5LYFNXM33NSLWXJBYFGJQNJ/bundle.json","state_url":"https://pith.science/pith/G6E5LYFNXM33NSLWXJBYFGJQNJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G6E5LYFNXM33NSLWXJBYFGJQNJ/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":"2026-08-13T04:08:28Z","links":{"resolver":"https://pith.science/pith/G6E5LYFNXM33NSLWXJBYFGJQNJ","bundle":"https://pith.science/pith/G6E5LYFNXM33NSLWXJBYFGJQNJ/bundle.json","state":"https://pith.science/pith/G6E5LYFNXM33NSLWXJBYFGJQNJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G6E5LYFNXM33NSLWXJBYFGJQNJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G6E5LYFNXM33NSLWXJBYFGJQNJ","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":"4841a811ff57d950aaa68209e57dac7e9cb09df8dd9a1faeabc9dbfe819812f8","cross_cats_sorted":["math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-11-10T08:36:31Z","title_canon_sha256":"2593cc6fc030120b1f0609a6f7e0da03629111db517e056e678891d71e842dc9"},"schema_version":"1.0","source":{"id":"2011.04970","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04970","created_at":"2026-07-05T01:50:42Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04970v1","created_at":"2026-07-05T01:50:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04970","created_at":"2026-07-05T01:50:42Z"},{"alias_kind":"pith_short_12","alias_value":"G6E5LYFNXM33","created_at":"2026-07-05T01:50:42Z"},{"alias_kind":"pith_short_16","alias_value":"G6E5LYFNXM33NSLW","created_at":"2026-07-05T01:50:42Z"},{"alias_kind":"pith_short_8","alias_value":"G6E5LYFN","created_at":"2026-07-05T01:50:42Z"}],"graph_snapshots":[{"event_id":"sha256:6b5dd4e0fbd4294847ca89b3d0e7d36caacc5ce48dcb45c8750e911f5d479bc4","target":"graph","created_at":"2026-07-05T01:50:42Z","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/2011.04970/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies an infinite horizon optimal control problem for discrete-time linear systems and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. A classical approach is to solve an algebraic Riccati equation that involves mathematical expectations and requires certain statistical information of the parameters. In this paper, we propose an online iterative algorithm in the spirit of Q-learning for the situation where only one random sample of parameters emerges at each time step. The first theorem proves the equivalence ","authors_text":"Fu Zhang, Kai Du, Qingxin Meng","cross_cats":["math.PR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-11-10T08:36:31Z","title":"A Q-learning algorithm for discrete-time linear-quadratic control with random parameters of unknown distribution: convergence and stabilization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04970","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":"sha256:2dd66dd9ff1b757cd3fb55c4f3382ed026b270020bbf70ee9a7ca1bf85499080","target":"record","created_at":"2026-07-05T01:50:42Z","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":"4841a811ff57d950aaa68209e57dac7e9cb09df8dd9a1faeabc9dbfe819812f8","cross_cats_sorted":["math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-11-10T08:36:31Z","title_canon_sha256":"2593cc6fc030120b1f0609a6f7e0da03629111db517e056e678891d71e842dc9"},"schema_version":"1.0","source":{"id":"2011.04970","kind":"arxiv","version":1}},"canonical_sha256":"3789d5e0adbb37b6c976ba438299306a4be020a704133b4fda54c1b4212a7b98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3789d5e0adbb37b6c976ba438299306a4be020a704133b4fda54c1b4212a7b98","first_computed_at":"2026-07-05T01:50:42.181119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:50:42.181119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XKO8mHY62HDixnuEpMsq2VPZgToS12w+MD/NtmB0HiorsuQHpQpstRRppnlgM3icLsZwgfL6/Wo3QaUuPWHjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:50:42.181544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.04970","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dd66dd9ff1b757cd3fb55c4f3382ed026b270020bbf70ee9a7ca1bf85499080","sha256:6b5dd4e0fbd4294847ca89b3d0e7d36caacc5ce48dcb45c8750e911f5d479bc4"],"state_sha256":"28e05b6ff61f52b8ad519b0a15f91ce101e3edf8187fea0f4f61148951bc9d32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZEu6oWRpA8JkRwysOpy17lMLN+9RC1EF1UbrTQO1YxL39ZXY5JFNXhNSDnjkrwPt7yDkiROM6zwv67u9P/CaCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:08:28.566084Z","bundle_sha256":"5ec730647c3ccbc7ab83df5cb5ba8db5a767344091f496fe82aa7f363d95509e"}}