{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YFU3YC7FCCFPBSN2BBHNDMQAH3","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":"152b5962dfc1d84d27446bd33b0ebc094d5cbf8b33538a53e9c9a6d19f6585d3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-01T19:48:57Z","title_canon_sha256":"5d710863cdfa6b6a5b44ebd8d076af3f0ba04ca39aed9e0dee4c4f72b162b7b2"},"schema_version":"1.0","source":{"id":"1911.00567","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.00567","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"arxiv_version","alias_value":"1911.00567v7","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00567","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"pith_short_12","alias_value":"YFU3YC7FCCFP","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"pith_short_16","alias_value":"YFU3YC7FCCFPBSN2","created_at":"2026-07-05T06:48:43Z"},{"alias_kind":"pith_short_8","alias_value":"YFU3YC7F","created_at":"2026-07-05T06:48:43Z"}],"graph_snapshots":[{"event_id":"sha256:ca6c46e772cf942ae6a0f4b5abc54beab283a99ccb7f8e0e22ca3edffd136123","target":"graph","created_at":"2026-07-05T06:48:43Z","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/1911.00567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning (RL). When the state space is large or continuous, traditional tabular approaches are unfeasible and some form of function approximation is mandatory. In this paper, we introduce an optimistically-initialized variant of the popular randomized least-squares value iteration (RLSVI), a model-free algorithm where exploration is induced by perturbing the least-squares approximation of the action-value function. Under the assumption that the Markov decision process has low-rank transition dynamics, we prove tha","authors_text":"Alessandro Lazaric, Andrea Zanette, David Brandfonbrener, Emma Brunskill, Matteo Pirotta","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-01T19:48:57Z","title":"Frequentist Regret Bounds for Randomized Least-Squares Value Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00567","kind":"arxiv","version":7},"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":"sha256:1dc682c2ecbc1fe74d54896767530b5a0cc7923a415fc5e889b8b8f7853f738c","target":"record","created_at":"2026-07-05T06:48:43Z","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":"152b5962dfc1d84d27446bd33b0ebc094d5cbf8b33538a53e9c9a6d19f6585d3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-01T19:48:57Z","title_canon_sha256":"5d710863cdfa6b6a5b44ebd8d076af3f0ba04ca39aed9e0dee4c4f72b162b7b2"},"schema_version":"1.0","source":{"id":"1911.00567","kind":"arxiv","version":7}},"canonical_sha256":"c169bc0be5108af0c9ba084ed1b2003ef19c3a2d0dc825bb0642ba1f50554062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c169bc0be5108af0c9ba084ed1b2003ef19c3a2d0dc825bb0642ba1f50554062","first_computed_at":"2026-07-05T06:48:43.879700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:43.879700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H7P2ilg1CRHZbsNu93k7YFgaAGocwvCWTUNN8Ot9HxKGqwZMuJ9b06Wyxwhpriex8pYaxe0Us51XaCaiGNkwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:43.880178Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.00567","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dc682c2ecbc1fe74d54896767530b5a0cc7923a415fc5e889b8b8f7853f738c","sha256:ca6c46e772cf942ae6a0f4b5abc54beab283a99ccb7f8e0e22ca3edffd136123"],"state_sha256":"8b8ec1e00b24aded336bab794990b31f1fc7b97a3f2afa5a96368aef6fba7dd1"}