{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PH3ESEJVWDZN4U2T2NARTEEIE2","short_pith_number":"pith:PH3ESEJV","schema_version":"1.0","canonical_sha256":"79f6491135b0f2de5353d34119908826839ff028549f1081c983b0c247be258e","source":{"kind":"arxiv","id":"2103.04416","version":1},"attestation_state":"computed","paper":{"title":"The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free, Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matthew E. Taylor, Sriram Ganapathi Subramanian, Volodymyr Tkachuk","submitted_at":"2021-03-07T18:20:47Z","abstract_excerpt":"Some reinforcement learning methods suffer from high sample complexity causing them to not be practical in real-world situations. $Q$-function reuse, a transfer learning method, is one way to reduce the sample complexity of learning, potentially improving usefulness of existing algorithms. Prior work has shown the empirical effectiveness of $Q$-function reuse for various environments when applied to model-free algorithms. To the best of our knowledge, there has been no theoretical work showing the regret of $Q$-function reuse when applied to the tabular, model-free setting. We aim to bridge th"},"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":"2103.04416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-07T18:20:47Z","cross_cats_sorted":[],"title_canon_sha256":"28fdd49033c492aa2fca784adff53dcaf47a2038444b6435f8ad69a788b20818","abstract_canon_sha256":"42a15c95afa24cb09f6b5791cf4d73ad64ca05fecf9db27d3d7697e94a0fa6d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:05.429541Z","signature_b64":"McO3cNrH/gVpB6kANjNkL2gsRa/ClVweAA2mH1RTITIfuauGT9i85nZ5QgLhK0wmWzYkryiJT2m2nGXiwxS6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79f6491135b0f2de5353d34119908826839ff028549f1081c983b0c247be258e","last_reissued_at":"2026-07-05T02:21:05.429145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:05.429145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free, Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matthew E. Taylor, Sriram Ganapathi Subramanian, Volodymyr Tkachuk","submitted_at":"2021-03-07T18:20:47Z","abstract_excerpt":"Some reinforcement learning methods suffer from high sample complexity causing them to not be practical in real-world situations. $Q$-function reuse, a transfer learning method, is one way to reduce the sample complexity of learning, potentially improving usefulness of existing algorithms. Prior work has shown the empirical effectiveness of $Q$-function reuse for various environments when applied to model-free algorithms. To the best of our knowledge, there has been no theoretical work showing the regret of $Q$-function reuse when applied to the tabular, model-free setting. We aim to bridge th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04416","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/2103.04416/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":"2103.04416","created_at":"2026-07-05T02:21:05.429201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.04416v1","created_at":"2026-07-05T02:21:05.429201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04416","created_at":"2026-07-05T02:21:05.429201+00:00"},{"alias_kind":"pith_short_12","alias_value":"PH3ESEJVWDZN","created_at":"2026-07-05T02:21:05.429201+00:00"},{"alias_kind":"pith_short_16","alias_value":"PH3ESEJVWDZN4U2T","created_at":"2026-07-05T02:21:05.429201+00:00"},{"alias_kind":"pith_short_8","alias_value":"PH3ESEJV","created_at":"2026-07-05T02:21:05.429201+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/PH3ESEJVWDZN4U2T2NARTEEIE2","json":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2.json","graph_json":"https://pith.science/api/pith-number/PH3ESEJVWDZN4U2T2NARTEEIE2/graph.json","events_json":"https://pith.science/api/pith-number/PH3ESEJVWDZN4U2T2NARTEEIE2/events.json","paper":"https://pith.science/paper/PH3ESEJV"},"agent_actions":{"view_html":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2","download_json":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2.json","view_paper":"https://pith.science/paper/PH3ESEJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.04416&json=true","fetch_graph":"https://pith.science/api/pith-number/PH3ESEJVWDZN4U2T2NARTEEIE2/graph.json","fetch_events":"https://pith.science/api/pith-number/PH3ESEJVWDZN4U2T2NARTEEIE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/action/storage_attestation","attest_author":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/action/author_attestation","sign_citation":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/action/citation_signature","submit_replication":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/action/replication_record"}},"created_at":"2026-07-05T02:21:05.429201+00:00","updated_at":"2026-07-05T02:21:05.429201+00:00"}