{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3GOZW37ZE4EH6JVASTMO347CAD","short_pith_number":"pith:3GOZW37Z","schema_version":"1.0","canonical_sha256":"d99d9b6ff927087f26a094d8edf3e200f65cac61e363e0aa1e66b55aa2ddef14","source":{"kind":"arxiv","id":"2102.09703","version":5},"attestation_state":"computed","paper":{"title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Maryam Fazel, Qiwen Cui, Ruoqi Shen, Simon S. Du, Zhihan Xiong","submitted_at":"2021-02-19T01:42:50Z","abstract_excerpt":"We study algorithms using randomized value functions for exploration in reinforcement learning. This type of algorithms enjoys appealing empirical performance. We show that when we use 1) a single random seed in each episode, and 2) a Bernstein-type magnitude of noise, we obtain a worst-case $\\widetilde{O}\\left(H\\sqrt{SAT}\\right)$ regret bound for episodic time-inhomogeneous Markov Decision Process where $S$ is the size of state space, $A$ is the size of action space, $H$ is the planning horizon and $T$ is the number of interactions. This bound polynomially improves all existing bounds for alg"},"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":"2102.09703","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-19T01:42:50Z","cross_cats_sorted":[],"title_canon_sha256":"5ee2288d712e6a1a9940e3b7a4b4278903d79f028c53f0e3b556e58d3c2933ff","abstract_canon_sha256":"8512f4aad4b2be7b5d997cdc216e079e6c313dedf9d25f6a17b497baa0a4ebd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:07.233868Z","signature_b64":"UyQgfYWxlB6P3ogXjBqEF/uI3w8dYkQgJ7b5EgT5csyQNQCk9MLjDTPOuF7XqtT89rOOaYnMPEaL2nfBZnr5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d99d9b6ff927087f26a094d8edf3e200f65cac61e363e0aa1e66b55aa2ddef14","last_reissued_at":"2026-07-05T05:06:07.233351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:07.233351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Maryam Fazel, Qiwen Cui, Ruoqi Shen, Simon S. Du, Zhihan Xiong","submitted_at":"2021-02-19T01:42:50Z","abstract_excerpt":"We study algorithms using randomized value functions for exploration in reinforcement learning. This type of algorithms enjoys appealing empirical performance. We show that when we use 1) a single random seed in each episode, and 2) a Bernstein-type magnitude of noise, we obtain a worst-case $\\widetilde{O}\\left(H\\sqrt{SAT}\\right)$ regret bound for episodic time-inhomogeneous Markov Decision Process where $S$ is the size of state space, $A$ is the size of action space, $H$ is the planning horizon and $T$ is the number of interactions. This bound polynomially improves all existing bounds for alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09703","kind":"arxiv","version":5},"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/2102.09703/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":"2102.09703","created_at":"2026-07-05T05:06:07.233414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09703v5","created_at":"2026-07-05T05:06:07.233414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09703","created_at":"2026-07-05T05:06:07.233414+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GOZW37ZE4EH","created_at":"2026-07-05T05:06:07.233414+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GOZW37ZE4EH6JVA","created_at":"2026-07-05T05:06:07.233414+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GOZW37Z","created_at":"2026-07-05T05:06:07.233414+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/3GOZW37ZE4EH6JVASTMO347CAD","json":"https://pith.science/pith/3GOZW37ZE4EH6JVASTMO347CAD.json","graph_json":"https://pith.science/api/pith-number/3GOZW37ZE4EH6JVASTMO347CAD/graph.json","events_json":"https://pith.science/api/pith-number/3GOZW37ZE4EH6JVASTMO347CAD/events.json","paper":"https://pith.science/paper/3GOZW37Z"},"agent_actions":{"view_html":"https://pith.science/pith/3GOZW37ZE4EH6JVASTMO347CAD","download_json":"https://pith.science/pith/3GOZW37ZE4EH6JVASTMO347CAD.json","view_paper":"https://pith.science/paper/3GOZW37Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09703&json=true","fetch_graph":"https://pith.science/api/pith-number/3GOZW37ZE4EH6JVASTMO347CAD/graph.json","fetch_events":"https://pith.science/api/pith-number/3GOZW37ZE4EH6JVASTMO347CAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GOZW37ZE4EH6JVASTMO347CAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GOZW37ZE4EH6JVASTMO347CAD/action/storage_attestation","attest_author":"https://pith.science/pith/3GOZW37ZE4EH6JVASTMO347CAD/action/author_attestation","sign_citation":"https://pith.science/pith/3GOZW37ZE4EH6JVASTMO347CAD/action/citation_signature","submit_replication":"https://pith.science/pith/3GOZW37ZE4EH6JVASTMO347CAD/action/replication_record"}},"created_at":"2026-07-05T05:06:07.233414+00:00","updated_at":"2026-07-05T05:06:07.233414+00:00"}