{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PH3ESEJVWDZN4U2T2NARTEEIE2","short_pith_number":"pith:PH3ESEJV","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"},"canonical_sha256":"79f6491135b0f2de5353d34119908826839ff028549f1081c983b0c247be258e","source":{"kind":"arxiv","id":"2103.04416","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04416","created_at":"2026-07-05T02:21:05Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04416v1","created_at":"2026-07-05T02:21:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04416","created_at":"2026-07-05T02:21:05Z"},{"alias_kind":"pith_short_12","alias_value":"PH3ESEJVWDZN","created_at":"2026-07-05T02:21:05Z"},{"alias_kind":"pith_short_16","alias_value":"PH3ESEJVWDZN4U2T","created_at":"2026-07-05T02:21:05Z"},{"alias_kind":"pith_short_8","alias_value":"PH3ESEJV","created_at":"2026-07-05T02:21:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PH3ESEJVWDZN4U2T2NARTEEIE2","target":"record","payload":{"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"},"canonical_sha256":"79f6491135b0f2de5353d34119908826839ff028549f1081c983b0c247be258e","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"},"source_kind":"arxiv","source_id":"2103.04416","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:21:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ia8pzt7CsrNS4Yd2K5FYORe4CGD7+pRMKCAKLM9NC1FNuW9lMeEWpsV91yNkWc2/B9sFNIaN6T2ck2CcZxPYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:49:48.616989Z"},"content_sha256":"170806910addcebc800879125287c98b0f78e03e2cc2b6acccb15898f7902419","schema_version":"1.0","event_id":"sha256:170806910addcebc800879125287c98b0f78e03e2cc2b6acccb15898f7902419"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PH3ESEJVWDZN4U2T2NARTEEIE2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:21:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2nKSQ9nX+SnUT6uZL6XQNnW5AUmiZeZ3tTxYe9QOs1IOG0JuFUWocSljPjbG8AKSXpvqT2+UE06fN3Y4KY1zCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:49:48.617683Z"},"content_sha256":"d2b2b7036ac440f710e00680c9069f31f0fb24e0129f0805d6125e0c71e214d3","schema_version":"1.0","event_id":"sha256:d2b2b7036ac440f710e00680c9069f31f0fb24e0129f0805d6125e0c71e214d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/bundle.json","state_url":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T20:49:48Z","links":{"resolver":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2","bundle":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/bundle.json","state":"https://pith.science/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PH3ESEJVWDZN4U2T2NARTEEIE2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PH3ESEJVWDZN4U2T2NARTEEIE2","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":"42a15c95afa24cb09f6b5791cf4d73ad64ca05fecf9db27d3d7697e94a0fa6d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-07T18:20:47Z","title_canon_sha256":"28fdd49033c492aa2fca784adff53dcaf47a2038444b6435f8ad69a788b20818"},"schema_version":"1.0","source":{"id":"2103.04416","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04416","created_at":"2026-07-05T02:21:05Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04416v1","created_at":"2026-07-05T02:21:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04416","created_at":"2026-07-05T02:21:05Z"},{"alias_kind":"pith_short_12","alias_value":"PH3ESEJVWDZN","created_at":"2026-07-05T02:21:05Z"},{"alias_kind":"pith_short_16","alias_value":"PH3ESEJVWDZN4U2T","created_at":"2026-07-05T02:21:05Z"},{"alias_kind":"pith_short_8","alias_value":"PH3ESEJV","created_at":"2026-07-05T02:21:05Z"}],"graph_snapshots":[{"event_id":"sha256:d2b2b7036ac440f710e00680c9069f31f0fb24e0129f0805d6125e0c71e214d3","target":"graph","created_at":"2026-07-05T02:21:05Z","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/2103.04416/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Matthew E. Taylor, Sriram Ganapathi Subramanian, Volodymyr Tkachuk","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-07T18:20:47Z","title":"The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free, Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04416","kind":"arxiv","version":1},"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":"sha256:170806910addcebc800879125287c98b0f78e03e2cc2b6acccb15898f7902419","target":"record","created_at":"2026-07-05T02:21:05Z","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":"42a15c95afa24cb09f6b5791cf4d73ad64ca05fecf9db27d3d7697e94a0fa6d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-07T18:20:47Z","title_canon_sha256":"28fdd49033c492aa2fca784adff53dcaf47a2038444b6435f8ad69a788b20818"},"schema_version":"1.0","source":{"id":"2103.04416","kind":"arxiv","version":1}},"canonical_sha256":"79f6491135b0f2de5353d34119908826839ff028549f1081c983b0c247be258e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79f6491135b0f2de5353d34119908826839ff028549f1081c983b0c247be258e","first_computed_at":"2026-07-05T02:21:05.429145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:21:05.429145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"McO3cNrH/gVpB6kANjNkL2gsRa/ClVweAA2mH1RTITIfuauGT9i85nZ5QgLhK0wmWzYkryiJT2m2nGXiwxS6Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:21:05.429541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.04416","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:170806910addcebc800879125287c98b0f78e03e2cc2b6acccb15898f7902419","sha256:d2b2b7036ac440f710e00680c9069f31f0fb24e0129f0805d6125e0c71e214d3"],"state_sha256":"a99acd76d6a56688cc50e21153025befef872fb89ad64dd339105bc584abb9ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZsTjOJcBtby9CVy6GsJaGSm7uaoRXm3BU+1gP0R6B9+prd9ilaDJfCnHBwivUSmH0A53oX+GXvw0yu/ZlXOBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:49:48.627273Z","bundle_sha256":"2e1e25ff08544eee4920c0fa2c780f19f265810d18a6d390ccaf3145cbbfd5ee"}}