{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:NLAZSR56YQPG2JYWFTRNPEQGWW","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":"06c753377824eaf3492e5189b259c791dda8df10ae1ed52bec30a6f9474ed14b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-09-26T12:36:00Z","title_canon_sha256":"e753e532f684ec6c98b171510a84b765751282d6cedc05f67b65f4146198ce3f"},"schema_version":"1.0","source":{"id":"1309.6821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1309.6821","created_at":"2026-05-18T03:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"1309.6821v1","created_at":"2026-05-18T03:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1309.6821","created_at":"2026-05-18T03:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"NLAZSR56YQPG","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"NLAZSR56YQPG2JYW","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"NLAZSR56","created_at":"2026-05-18T12:27:52Z"}],"graph_snapshots":[{"event_id":"sha256:0e51cd3d746f1ad696e73ce1a68ef47933fc47fe8746e60f13b527de14ce2f10","target":"graph","created_at":"2026-05-18T03:12:10Z","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":"Transferring knowledge across a sequence of reinforcement-learning tasks is challenging, and has a number of important applications. Though there is encouraging empirical evidence that transfer can improve performance in subsequent reinforcement-learning tasks, there has been very little theoretical analysis. In this paper, we introduce a new multi-task algorithm for a sequence of reinforcement-learning tasks when each task is sampled independently from (an unknown) distribution over a finite set of Markov decision processes whose parameters are initially unknown. For this setting, we prove un","authors_text":"Emma Brunskill, Lihong Li","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-09-26T12:36:00Z","title":"Sample Complexity of Multi-task Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1309.6821","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":"sha256:6980a40fa5c0ca5e33f256202b52edc56f383be9a97d18b51d5b891997fd088d","target":"record","created_at":"2026-05-18T03:12:10Z","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":"06c753377824eaf3492e5189b259c791dda8df10ae1ed52bec30a6f9474ed14b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-09-26T12:36:00Z","title_canon_sha256":"e753e532f684ec6c98b171510a84b765751282d6cedc05f67b65f4146198ce3f"},"schema_version":"1.0","source":{"id":"1309.6821","kind":"arxiv","version":1}},"canonical_sha256":"6ac19947bec41e6d27162ce2d79206b5a35ca72fb7e2451e66f827216b5bfad4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ac19947bec41e6d27162ce2d79206b5a35ca72fb7e2451e66f827216b5bfad4","first_computed_at":"2026-05-18T03:12:10.339490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:12:10.339490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2EBU9At1ktupa/ZEGv4bzzu8GSauK8Dk3nCzMxZXd4dpZa8avI+2y90WJ6fqx43uyVFiCi1KiMmMqPE+Ap1wCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:12:10.340358Z","signed_message":"canonical_sha256_bytes"},"source_id":"1309.6821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6980a40fa5c0ca5e33f256202b52edc56f383be9a97d18b51d5b891997fd088d","sha256:0e51cd3d746f1ad696e73ce1a68ef47933fc47fe8746e60f13b527de14ce2f10"],"state_sha256":"1d6379a393e375d85b238bfda70332aae12885630580dbf42e7e8eb6fe3b2d2e"}