{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5END7BQIJ2UCDIJDSYN63377T7","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":"a89bb7317c0f85ef5dd04b98dc6fdacbc0772c3edd5b6d19e4168713208d05b4","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-27T21:58:45Z","title_canon_sha256":"7df27d4f349620304950145b904886fe0c52115b9b418dcd95d4806a3c095729"},"schema_version":"1.0","source":{"id":"2312.16730","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16730","created_at":"2026-07-05T07:28:34Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16730v1","created_at":"2026-07-05T07:28:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16730","created_at":"2026-07-05T07:28:34Z"},{"alias_kind":"pith_short_12","alias_value":"5END7BQIJ2UC","created_at":"2026-07-05T07:28:34Z"},{"alias_kind":"pith_short_16","alias_value":"5END7BQIJ2UCDIJD","created_at":"2026-07-05T07:28:34Z"},{"alias_kind":"pith_short_8","alias_value":"5END7BQI","created_at":"2026-07-05T07:28:34Z"}],"graph_snapshots":[{"event_id":"sha256:2996f32e6782b52679bb2325979af931b67d2704b2b687ea3ab4bb32bd5b2cd9","target":"graph","created_at":"2026-07-05T07:28:34Z","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/2312.16730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"These lecture notes give a statistical perspective on the foundations of reinforcement learning and interactive decision making. We present a unifying framework for addressing the exploration-exploitation dilemma using frequentist and Bayesian approaches, with connections and parallels between supervised learning/estimation and decision making as an overarching theme. Special attention is paid to function approximation and flexible model classes such as neural networks. Topics covered include multi-armed and contextual bandits, structured bandits, and reinforcement learning with high-dimension","authors_text":"Alexander Rakhlin, Dylan J. Foster","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-27T21:58:45Z","title":"Foundations of Reinforcement Learning and Interactive Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16730","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":"sha256:6523a61d159d0d598127b8d27a61f3a2f9ab9c9f4142755266cbb27f625fd105","target":"record","created_at":"2026-07-05T07:28:34Z","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":"a89bb7317c0f85ef5dd04b98dc6fdacbc0772c3edd5b6d19e4168713208d05b4","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-27T21:58:45Z","title_canon_sha256":"7df27d4f349620304950145b904886fe0c52115b9b418dcd95d4806a3c095729"},"schema_version":"1.0","source":{"id":"2312.16730","kind":"arxiv","version":1}},"canonical_sha256":"e91a3f86084ea821a123961bedefff9fef8a6ef3e797a76767c53926f60355f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e91a3f86084ea821a123961bedefff9fef8a6ef3e797a76767c53926f60355f0","first_computed_at":"2026-07-05T07:28:34.593072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:34.593072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+N1N8+0E1cg4Vzp/TOPDhj6OE86ja+iPHbaSZSGb79hVKNNNZzqhBIyFcQrvnSroIu1PdY6V8a8p5nT4CfjCBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:34.593571Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16730","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6523a61d159d0d598127b8d27a61f3a2f9ab9c9f4142755266cbb27f625fd105","sha256:2996f32e6782b52679bb2325979af931b67d2704b2b687ea3ab4bb32bd5b2cd9"],"state_sha256":"543e3ad05d0fa5293e0bfe4a5881f99cc09e284abbcbf55e10a5761b50af44d6"}