{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CMWYBGEZR45HVYWVDA2AOVL57X","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":"a005b52e933829d959323b8a4015262644ddb5159fb8e01937a2c18173f4053b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T13:01:42Z","title_canon_sha256":"1c90f65c36258ed1f4ed71d64e6d15f6b0d4afedfbf5f6976088ce323c2ee0d8"},"schema_version":"1.0","source":{"id":"2306.07745","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07745","created_at":"2026-07-05T07:55:57Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07745v3","created_at":"2026-07-05T07:55:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07745","created_at":"2026-07-05T07:55:57Z"},{"alias_kind":"pith_short_12","alias_value":"CMWYBGEZR45H","created_at":"2026-07-05T07:55:57Z"},{"alias_kind":"pith_short_16","alias_value":"CMWYBGEZR45HVYWV","created_at":"2026-07-05T07:55:57Z"},{"alias_kind":"pith_short_8","alias_value":"CMWYBGEZ","created_at":"2026-07-05T07:55:57Z"}],"graph_snapshots":[{"event_id":"sha256:ca0d3ff9bf2682d65f6df4f92e5248f8b1a43ae3ef718da0c67603fe1e11db9b","target":"graph","created_at":"2026-07-05T07:55:57Z","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/2306.07745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Julia Olkhovskaya, Sattar Vakili","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T13:01:42Z","title":"Kernelized Reinforcement Learning with Order Optimal Regret Bounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07745","kind":"arxiv","version":3},"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":"sha256:391f7623d323465cab0a55883684eaa00b66123c1b2984c7f04f0e8a0fdfb683","target":"record","created_at":"2026-07-05T07:55:57Z","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":"a005b52e933829d959323b8a4015262644ddb5159fb8e01937a2c18173f4053b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T13:01:42Z","title_canon_sha256":"1c90f65c36258ed1f4ed71d64e6d15f6b0d4afedfbf5f6976088ce323c2ee0d8"},"schema_version":"1.0","source":{"id":"2306.07745","kind":"arxiv","version":3}},"canonical_sha256":"132d8098998f3a7ae2d5183407557dfdd96c2fbd906d34dc585c6e805bd5f4e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"132d8098998f3a7ae2d5183407557dfdd96c2fbd906d34dc585c6e805bd5f4e3","first_computed_at":"2026-07-05T07:55:57.984082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:57.984082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GS2Sz8hygyM4ldBch4LIBl1VwvQbFkRdQXSX7FQDARjo6DjU/WwpIqdyocfVDyJVKSVC2uroTL9XOsN9YNw2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:57.984561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07745","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:391f7623d323465cab0a55883684eaa00b66123c1b2984c7f04f0e8a0fdfb683","sha256:ca0d3ff9bf2682d65f6df4f92e5248f8b1a43ae3ef718da0c67603fe1e11db9b"],"state_sha256":"10288e0b62986e0fb4d6dc590cedc670c2da19b7695525d301ad35c31c7a21bb"}