{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5END7BQIJ2UCDIJDSYN63377T7","short_pith_number":"pith:5END7BQI","schema_version":"1.0","canonical_sha256":"e91a3f86084ea821a123961bedefff9fef8a6ef3e797a76767c53926f60355f0","source":{"kind":"arxiv","id":"2312.16730","version":1},"attestation_state":"computed","paper":{"title":"Foundations of Reinforcement Learning and Interactive Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Dylan J. Foster","submitted_at":"2023-12-27T21:58:45Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.16730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-27T21:58:45Z","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"7df27d4f349620304950145b904886fe0c52115b9b418dcd95d4806a3c095729","abstract_canon_sha256":"a89bb7317c0f85ef5dd04b98dc6fdacbc0772c3edd5b6d19e4168713208d05b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:34.593571Z","signature_b64":"+N1N8+0E1cg4Vzp/TOPDhj6OE86ja+iPHbaSZSGb79hVKNNNZzqhBIyFcQrvnSroIu1PdY6V8a8p5nT4CfjCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e91a3f86084ea821a123961bedefff9fef8a6ef3e797a76767c53926f60355f0","last_reissued_at":"2026-07-05T07:28:34.593072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:34.593072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foundations of Reinforcement Learning and Interactive Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Dylan J. Foster","submitted_at":"2023-12-27T21:58:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16730","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/2312.16730/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.16730","created_at":"2026-07-05T07:28:34.593127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16730v1","created_at":"2026-07-05T07:28:34.593127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16730","created_at":"2026-07-05T07:28:34.593127+00:00"},{"alias_kind":"pith_short_12","alias_value":"5END7BQIJ2UC","created_at":"2026-07-05T07:28:34.593127+00:00"},{"alias_kind":"pith_short_16","alias_value":"5END7BQIJ2UCDIJD","created_at":"2026-07-05T07:28:34.593127+00:00"},{"alias_kind":"pith_short_8","alias_value":"5END7BQI","created_at":"2026-07-05T07:28:34.593127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18531","citing_title":"When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01382","citing_title":"Efficient Exploration for Iterative Nash Preference Optimization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30445","citing_title":"When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21107","citing_title":"Improved Guarantees for Constrained Online Convex Optimization via Self-Contraction","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09214","citing_title":"Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06190","citing_title":"Constrained Contextual Bandits with Adversarial Contexts","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5END7BQIJ2UCDIJDSYN63377T7","json":"https://pith.science/pith/5END7BQIJ2UCDIJDSYN63377T7.json","graph_json":"https://pith.science/api/pith-number/5END7BQIJ2UCDIJDSYN63377T7/graph.json","events_json":"https://pith.science/api/pith-number/5END7BQIJ2UCDIJDSYN63377T7/events.json","paper":"https://pith.science/paper/5END7BQI"},"agent_actions":{"view_html":"https://pith.science/pith/5END7BQIJ2UCDIJDSYN63377T7","download_json":"https://pith.science/pith/5END7BQIJ2UCDIJDSYN63377T7.json","view_paper":"https://pith.science/paper/5END7BQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16730&json=true","fetch_graph":"https://pith.science/api/pith-number/5END7BQIJ2UCDIJDSYN63377T7/graph.json","fetch_events":"https://pith.science/api/pith-number/5END7BQIJ2UCDIJDSYN63377T7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5END7BQIJ2UCDIJDSYN63377T7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5END7BQIJ2UCDIJDSYN63377T7/action/storage_attestation","attest_author":"https://pith.science/pith/5END7BQIJ2UCDIJDSYN63377T7/action/author_attestation","sign_citation":"https://pith.science/pith/5END7BQIJ2UCDIJDSYN63377T7/action/citation_signature","submit_replication":"https://pith.science/pith/5END7BQIJ2UCDIJDSYN63377T7/action/replication_record"}},"created_at":"2026-07-05T07:28:34.593127+00:00","updated_at":"2026-07-05T07:28:34.593127+00:00"}