{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:JO7Z52QN3JI67UP6TDLLOPEA2H","short_pith_number":"pith:JO7Z52QN","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"},"canonical_sha256":"4bbf9eea0dda51efd1fe98d6b73c80d1fb70c438859f8a996f49aea4a2a5bb91","source":{"kind":"arxiv","id":"1507.00436","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.00436","created_at":"2026-05-18T01:36:49Z"},{"alias_kind":"arxiv_version","alias_value":"1507.00436v2","created_at":"2026-05-18T01:36:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00436","created_at":"2026-05-18T01:36:49Z"},{"alias_kind":"pith_short_12","alias_value":"JO7Z52QN3JI6","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"JO7Z52QN3JI67UP6","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"JO7Z52QN","created_at":"2026-05-18T12:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:JO7Z52QN3JI67UP6TDLLOPEA2H","target":"record","payload":{"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"},"canonical_sha256":"4bbf9eea0dda51efd1fe98d6b73c80d1fb70c438859f8a996f49aea4a2a5bb91","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"},"source_kind":"arxiv","source_id":"1507.00436","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:36:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k+Sskps3lJACeX8gkNyAB0cImUf/BxCYtQPt1fTcZKEPIN19QBGeKWGv+gosBX6qAQxL7UZ0ECGJ3t8F0ck/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T07:36:55.454903Z"},"content_sha256":"4dc622ff152275114b179660896dbd22ff84a89cdde03b1eed9a94520ade7c10","schema_version":"1.0","event_id":"sha256:4dc622ff152275114b179660896dbd22ff84a89cdde03b1eed9a94520ade7c10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:JO7Z52QN3JI67UP6TDLLOPEA2H","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:36:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"52Q0jURrWEblbznre4FrNgp7Rmcul1iGkdpxHdlFTZv/8LmtIfBl2P7Whig457k7EcVjoHWuBdXlK0srlmftBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T07:36:55.455252Z"},"content_sha256":"c569111669759d1b4db572a2d21a605c041ed87c82244c10023f14f13eb6e6c6","schema_version":"1.0","event_id":"sha256:c569111669759d1b4db572a2d21a605c041ed87c82244c10023f14f13eb6e6c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/bundle.json","state_url":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/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":"2026-06-21T07:36:55Z","links":{"resolver":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H","bundle":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/bundle.json","state":"https://pith.science/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JO7Z52QN3JI67UP6TDLLOPEA2H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:JO7Z52QN3JI67UP6TDLLOPEA2H","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":"53ea8222ed2b34528929204657a45f7da5164d359b9cd61a8eb34d8f62ea3b77","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2015-07-02T06:05:44Z","title_canon_sha256":"78db23204aaf69daf46871f5cad80d09320437b28062fbea631a15f0ba4d6c90"},"schema_version":"1.0","source":{"id":"1507.00436","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.00436","created_at":"2026-05-18T01:36:49Z"},{"alias_kind":"arxiv_version","alias_value":"1507.00436v2","created_at":"2026-05-18T01:36:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00436","created_at":"2026-05-18T01:36:49Z"},{"alias_kind":"pith_short_12","alias_value":"JO7Z52QN3JI6","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"JO7Z52QN3JI67UP6","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"JO7Z52QN","created_at":"2026-05-18T12:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:c569111669759d1b4db572a2d21a605c041ed87c82244c10023f14f13eb6e6c6","target":"graph","created_at":"2026-05-18T01:36:49Z","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"},"paper":{"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","authors_text":"Matthew E. Taylor, Yusen Zhan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2015-07-02T06:05:44Z","title":"Online Transfer Learning in Reinforcement Learning Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00436","kind":"arxiv","version":2},"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":"sha256:4dc622ff152275114b179660896dbd22ff84a89cdde03b1eed9a94520ade7c10","target":"record","created_at":"2026-05-18T01:36:49Z","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":"53ea8222ed2b34528929204657a45f7da5164d359b9cd61a8eb34d8f62ea3b77","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2015-07-02T06:05:44Z","title_canon_sha256":"78db23204aaf69daf46871f5cad80d09320437b28062fbea631a15f0ba4d6c90"},"schema_version":"1.0","source":{"id":"1507.00436","kind":"arxiv","version":2}},"canonical_sha256":"4bbf9eea0dda51efd1fe98d6b73c80d1fb70c438859f8a996f49aea4a2a5bb91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bbf9eea0dda51efd1fe98d6b73c80d1fb70c438859f8a996f49aea4a2a5bb91","first_computed_at":"2026-05-18T01:36:49.505075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:36:49.505075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wAOcDMpnTtGgFZeIRtnxpOufTmHI8j6jpL9w1x9/KLkc0R9FgeHMQ4oh0FZQKNTHBJkI8dbRdAdXALDJWi38AA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:36:49.505701Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.00436","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4dc622ff152275114b179660896dbd22ff84a89cdde03b1eed9a94520ade7c10","sha256:c569111669759d1b4db572a2d21a605c041ed87c82244c10023f14f13eb6e6c6"],"state_sha256":"670feaab2e2922d89d9f7ac5bad510aa59f0681bf977732235c231e08ee22918"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hpMgQYpXY48oXo3rqx1GDb39B6Xq/oLqbtef/k9px4+MkAHz+UE5SdzekEX19/ZM8XfwatZjJoT+2ZxKF7OXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-21T07:36:55.457156Z","bundle_sha256":"973a8a8b690f27e55d6d346a6defa4082e044c73e5e1c32508dc1f3fcfa83c2b"}}