{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:JO7Z52QN3JI67UP6TDLLOPEA2H","short_pith_number":"pith:JO7Z52QN","schema_version":"1.0","canonical_sha256":"4bbf9eea0dda51efd1fe98d6b73c80d1fb70c438859f8a996f49aea4a2a5bb91","source":{"kind":"arxiv","id":"1507.00436","version":2},"attestation_state":"computed","paper":{"title":"Online Transfer Learning in Reinforcement Learning Domains","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Matthew E. Taylor, Yusen Zhan","submitted_at":"2015-07-02T06:05:44Z","abstract_excerpt":"This paper proposes an online transfer framework to capture the interaction among agents and shows that current transfer learning in reinforcement learning is a special case of online transfer. Furthermore, this paper re-characterizes existing agents-teaching-agents methods as online transfer and analyze one such teaching method in three ways. First, the convergence of Q-learning and Sarsa with tabular representation with a finite budget is proven. Second, the convergence of Q-learning and Sarsa with linear function approximation is established. Third, the we show the asymptotic performance ca"},"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":"1507.00436","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2015-07-02T06:05:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"78db23204aaf69daf46871f5cad80d09320437b28062fbea631a15f0ba4d6c90","abstract_canon_sha256":"53ea8222ed2b34528929204657a45f7da5164d359b9cd61a8eb34d8f62ea3b77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:49.505701Z","signature_b64":"wAOcDMpnTtGgFZeIRtnxpOufTmHI8j6jpL9w1x9/KLkc0R9FgeHMQ4oh0FZQKNTHBJkI8dbRdAdXALDJWi38AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bbf9eea0dda51efd1fe98d6b73c80d1fb70c438859f8a996f49aea4a2a5bb91","last_reissued_at":"2026-05-18T01:36:49.505075Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:49.505075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Transfer Learning in Reinforcement Learning Domains","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Matthew E. Taylor, Yusen Zhan","submitted_at":"2015-07-02T06:05:44Z","abstract_excerpt":"This paper proposes an online transfer framework to capture the interaction among agents and shows that current transfer learning in reinforcement learning is a special case of online transfer. Furthermore, this paper re-characterizes existing agents-teaching-agents methods as online transfer and analyze one such teaching method in three ways. First, the convergence of Q-learning and Sarsa with tabular representation with a finite budget is proven. Second, the convergence of Q-learning and Sarsa with linear function approximation is established. Third, the we show the asymptotic performance ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00436","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1507.00436","created_at":"2026-05-18T01:36:49.505166+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.00436v2","created_at":"2026-05-18T01:36:49.505166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00436","created_at":"2026-05-18T01:36:49.505166+00:00"},{"alias_kind":"pith_short_12","alias_value":"JO7Z52QN3JI6","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"JO7Z52QN3JI67UP6","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"JO7Z52QN","created_at":"2026-05-18T12:29:27.538025+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/JO7Z52QN3JI67UP6TDLLOPEA2H","json":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H.json","graph_json":"https://pith.science/api/pith-number/JO7Z52QN3JI67UP6TDLLOPEA2H/graph.json","events_json":"https://pith.science/api/pith-number/JO7Z52QN3JI67UP6TDLLOPEA2H/events.json","paper":"https://pith.science/paper/JO7Z52QN"},"agent_actions":{"view_html":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H","download_json":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H.json","view_paper":"https://pith.science/paper/JO7Z52QN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.00436&json=true","fetch_graph":"https://pith.science/api/pith-number/JO7Z52QN3JI67UP6TDLLOPEA2H/graph.json","fetch_events":"https://pith.science/api/pith-number/JO7Z52QN3JI67UP6TDLLOPEA2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/action/storage_attestation","attest_author":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/action/author_attestation","sign_citation":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/action/citation_signature","submit_replication":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/action/replication_record"}},"created_at":"2026-05-18T01:36:49.505166+00:00","updated_at":"2026-05-18T01:36:49.505166+00:00"}