{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CMWYBGEZR45HVYWVDA2AOVL57X","short_pith_number":"pith:CMWYBGEZ","schema_version":"1.0","canonical_sha256":"132d8098998f3a7ae2d5183407557dfdd96c2fbd906d34dc585c6e805bd5f4e3","source":{"kind":"arxiv","id":"2306.07745","version":3},"attestation_state":"computed","paper":{"title":"Kernelized Reinforcement Learning with Order Optimal Regret Bounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Julia Olkhovskaya, Sattar Vakili","submitted_at":"2023-06-13T13:01:42Z","abstract_excerpt":"Reinforcement learning (RL) has shown empirical success in various real world settings with complex models and large state-action spaces. The existing analytical results, however, typically focus on settings with a small number of state-actions or simple models such as linearly modeled state-action value functions. To derive RL policies that efficiently handle large state-action spaces with more general value functions, some recent works have considered nonlinear function approximation using kernel ridge regression. We propose $\\pi$-KRVI, an optimistic modification of least-squares value itera"},"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":"2306.07745","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T13:01:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1c90f65c36258ed1f4ed71d64e6d15f6b0d4afedfbf5f6976088ce323c2ee0d8","abstract_canon_sha256":"a005b52e933829d959323b8a4015262644ddb5159fb8e01937a2c18173f4053b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:57.984561Z","signature_b64":"GS2Sz8hygyM4ldBch4LIBl1VwvQbFkRdQXSX7FQDARjo6DjU/WwpIqdyocfVDyJVKSVC2uroTL9XOsN9YNw2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"132d8098998f3a7ae2d5183407557dfdd96c2fbd906d34dc585c6e805bd5f4e3","last_reissued_at":"2026-07-05T07:55:57.984082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:57.984082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kernelized Reinforcement Learning with Order Optimal Regret Bounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Julia Olkhovskaya, Sattar Vakili","submitted_at":"2023-06-13T13:01:42Z","abstract_excerpt":"Reinforcement learning (RL) has shown empirical success in various real world settings with complex models and large state-action spaces. The existing analytical results, however, typically focus on settings with a small number of state-actions or simple models such as linearly modeled state-action value functions. To derive RL policies that efficiently handle large state-action spaces with more general value functions, some recent works have considered nonlinear function approximation using kernel ridge regression. We propose $\\pi$-KRVI, an optimistic modification of least-squares value itera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07745","kind":"arxiv","version":3},"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/2306.07745/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":"2306.07745","created_at":"2026-07-05T07:55:57.984140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07745v3","created_at":"2026-07-05T07:55:57.984140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07745","created_at":"2026-07-05T07:55:57.984140+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMWYBGEZR45H","created_at":"2026-07-05T07:55:57.984140+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMWYBGEZR45HVYWV","created_at":"2026-07-05T07:55:57.984140+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMWYBGEZ","created_at":"2026-07-05T07:55:57.984140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMWYBGEZR45HVYWVDA2AOVL57X","json":"https://pith.science/pith/CMWYBGEZR45HVYWVDA2AOVL57X.json","graph_json":"https://pith.science/api/pith-number/CMWYBGEZR45HVYWVDA2AOVL57X/graph.json","events_json":"https://pith.science/api/pith-number/CMWYBGEZR45HVYWVDA2AOVL57X/events.json","paper":"https://pith.science/paper/CMWYBGEZ"},"agent_actions":{"view_html":"https://pith.science/pith/CMWYBGEZR45HVYWVDA2AOVL57X","download_json":"https://pith.science/pith/CMWYBGEZR45HVYWVDA2AOVL57X.json","view_paper":"https://pith.science/paper/CMWYBGEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07745&json=true","fetch_graph":"https://pith.science/api/pith-number/CMWYBGEZR45HVYWVDA2AOVL57X/graph.json","fetch_events":"https://pith.science/api/pith-number/CMWYBGEZR45HVYWVDA2AOVL57X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMWYBGEZR45HVYWVDA2AOVL57X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMWYBGEZR45HVYWVDA2AOVL57X/action/storage_attestation","attest_author":"https://pith.science/pith/CMWYBGEZR45HVYWVDA2AOVL57X/action/author_attestation","sign_citation":"https://pith.science/pith/CMWYBGEZR45HVYWVDA2AOVL57X/action/citation_signature","submit_replication":"https://pith.science/pith/CMWYBGEZR45HVYWVDA2AOVL57X/action/replication_record"}},"created_at":"2026-07-05T07:55:57.984140+00:00","updated_at":"2026-07-05T07:55:57.984140+00:00"}