{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H47V7ZBN5TLNWBIDQPPPPCE55U","short_pith_number":"pith:H47V7ZBN","canonical_record":{"source":{"id":"2307.02632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T20:04:26Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"185835ff4d773a60b85cddab1a717bb17a55b5742d0532fbb9481ae3c8acaf2b","abstract_canon_sha256":"a2b9ac1b7c83dec326a3f2c3c4fc2e09cc5965a261eaa257d4d284a78138f6f2"},"schema_version":"1.0"},"canonical_sha256":"3f3f5fe42decd6db050383def7889ded22259228c431f60373815201797d7b43","source":{"kind":"arxiv","id":"2307.02632","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02632","created_at":"2026-07-05T06:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02632v2","created_at":"2026-07-05T06:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02632","created_at":"2026-07-05T06:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"H47V7ZBN5TLN","created_at":"2026-07-05T06:43:04Z"},{"alias_kind":"pith_short_16","alias_value":"H47V7ZBN5TLNWBID","created_at":"2026-07-05T06:43:04Z"},{"alias_kind":"pith_short_8","alias_value":"H47V7ZBN","created_at":"2026-07-05T06:43:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H47V7ZBN5TLNWBIDQPPPPCE55U","target":"record","payload":{"canonical_record":{"source":{"id":"2307.02632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T20:04:26Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"185835ff4d773a60b85cddab1a717bb17a55b5742d0532fbb9481ae3c8acaf2b","abstract_canon_sha256":"a2b9ac1b7c83dec326a3f2c3c4fc2e09cc5965a261eaa257d4d284a78138f6f2"},"schema_version":"1.0"},"canonical_sha256":"3f3f5fe42decd6db050383def7889ded22259228c431f60373815201797d7b43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:04.045144Z","signature_b64":"qJ8ug1LSHc1LGBP4V5okmP1cc3dUW2LcIGX3AWZbmG0xXitT1T4hgvsOcsNn54mpDOO+Hy73KY8hnq+Y2ayzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f3f5fe42decd6db050383def7889ded22259228c431f60373815201797d7b43","last_reissued_at":"2026-07-05T06:43:04.044710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:04.044710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.02632","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lm+jAlExrsHWxH3ASg3c1P/uKZZh/cvM6R5L6tp9t4FhfRBiyk6zapyXOchTNshH9ZQPGjn+qzX5sSVF8sTbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:56:39.313010Z"},"content_sha256":"b17b9590e3fe39e67218c0ec5b48250d5fd05d39cbd85c799474acf3cae543ef","schema_version":"1.0","event_id":"sha256:b17b9590e3fe39e67218c0ec5b48250d5fd05d39cbd85c799474acf3cae543ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H47V7ZBN5TLNWBIDQPPPPCE55U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stability of Q-Learning Through Design and Optimism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Sean Meyn","submitted_at":"2023-07-05T20:04:26Z","abstract_excerpt":"Q-learning has become an important part of the reinforcement learning toolkit since its introduction in the dissertation of Chris Watkins in the 1980s. The purpose of this paper is in part a tutorial on stochastic approximation and Q-learning, providing details regarding the INFORMS APS inaugural Applied Probability Trust Plenary Lecture, presented in Nancy France, June 2023.\n  The paper also presents new approaches to ensure stability and potentially accelerated convergence for these algorithms, and stochastic approximation in other settings. Two contributions are entirely new:\n  1. Stability"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02632","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.02632/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":"2026-07-05T06:43:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cWnIJB930hGd6uicjWDps+WEUDk/021kplq3yATgHZDjUIicvavaqSP3uwI7cNQTpAvMUDOlh1Kjg3K8P3flBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:56:39.313553Z"},"content_sha256":"f069e2f28f1a9d5d07d2562d5e849359f54bbec346d86224eb8a0d543bddcd38","schema_version":"1.0","event_id":"sha256:f069e2f28f1a9d5d07d2562d5e849359f54bbec346d86224eb8a0d543bddcd38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H47V7ZBN5TLNWBIDQPPPPCE55U/bundle.json","state_url":"https://pith.science/pith/H47V7ZBN5TLNWBIDQPPPPCE55U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H47V7ZBN5TLNWBIDQPPPPCE55U/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":"2026-08-10T05:56:39Z","links":{"resolver":"https://pith.science/pith/H47V7ZBN5TLNWBIDQPPPPCE55U","bundle":"https://pith.science/pith/H47V7ZBN5TLNWBIDQPPPPCE55U/bundle.json","state":"https://pith.science/pith/H47V7ZBN5TLNWBIDQPPPPCE55U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H47V7ZBN5TLNWBIDQPPPPCE55U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H47V7ZBN5TLNWBIDQPPPPCE55U","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":"a2b9ac1b7c83dec326a3f2c3c4fc2e09cc5965a261eaa257d4d284a78138f6f2","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T20:04:26Z","title_canon_sha256":"185835ff4d773a60b85cddab1a717bb17a55b5742d0532fbb9481ae3c8acaf2b"},"schema_version":"1.0","source":{"id":"2307.02632","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02632","created_at":"2026-07-05T06:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02632v2","created_at":"2026-07-05T06:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02632","created_at":"2026-07-05T06:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"H47V7ZBN5TLN","created_at":"2026-07-05T06:43:04Z"},{"alias_kind":"pith_short_16","alias_value":"H47V7ZBN5TLNWBID","created_at":"2026-07-05T06:43:04Z"},{"alias_kind":"pith_short_8","alias_value":"H47V7ZBN","created_at":"2026-07-05T06:43:04Z"}],"graph_snapshots":[{"event_id":"sha256:f069e2f28f1a9d5d07d2562d5e849359f54bbec346d86224eb8a0d543bddcd38","target":"graph","created_at":"2026-07-05T06:43:04Z","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/2307.02632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Q-learning has become an important part of the reinforcement learning toolkit since its introduction in the dissertation of Chris Watkins in the 1980s. The purpose of this paper is in part a tutorial on stochastic approximation and Q-learning, providing details regarding the INFORMS APS inaugural Applied Probability Trust Plenary Lecture, presented in Nancy France, June 2023.\n  The paper also presents new approaches to ensure stability and potentially accelerated convergence for these algorithms, and stochastic approximation in other settings. Two contributions are entirely new:\n  1. Stability","authors_text":"Sean Meyn","cross_cats":["cs.SY","eess.SY","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T20:04:26Z","title":"Stability of Q-Learning Through Design and Optimism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02632","kind":"arxiv","version":2},"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:b17b9590e3fe39e67218c0ec5b48250d5fd05d39cbd85c799474acf3cae543ef","target":"record","created_at":"2026-07-05T06:43:04Z","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":"a2b9ac1b7c83dec326a3f2c3c4fc2e09cc5965a261eaa257d4d284a78138f6f2","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T20:04:26Z","title_canon_sha256":"185835ff4d773a60b85cddab1a717bb17a55b5742d0532fbb9481ae3c8acaf2b"},"schema_version":"1.0","source":{"id":"2307.02632","kind":"arxiv","version":2}},"canonical_sha256":"3f3f5fe42decd6db050383def7889ded22259228c431f60373815201797d7b43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f3f5fe42decd6db050383def7889ded22259228c431f60373815201797d7b43","first_computed_at":"2026-07-05T06:43:04.044710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:04.044710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qJ8ug1LSHc1LGBP4V5okmP1cc3dUW2LcIGX3AWZbmG0xXitT1T4hgvsOcsNn54mpDOO+Hy73KY8hnq+Y2ayzBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:04.045144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.02632","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b17b9590e3fe39e67218c0ec5b48250d5fd05d39cbd85c799474acf3cae543ef","sha256:f069e2f28f1a9d5d07d2562d5e849359f54bbec346d86224eb8a0d543bddcd38"],"state_sha256":"56e7afd0aebfee3c866be352b97184aa858a22eeca0be32320e9a11e8b458c27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ZUis7/kW0BuqzNzeU9ZQHWf9MmCGQmWFIPK+5eMFzzDVTLYLxVGX3GELZZWlfgx2qrYwB7b0mx4thHrbSGOBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:56:39.319566Z","bundle_sha256":"f883d756dd31d65a8e667c00095d66bdfaa180d13fc818908ce8daf2137aa856"}}