{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:NLAZSR56YQPG2JYWFTRNPEQGWW","short_pith_number":"pith:NLAZSR56","schema_version":"1.0","canonical_sha256":"6ac19947bec41e6d27162ce2d79206b5a35ca72fb7e2451e66f827216b5bfad4","source":{"kind":"arxiv","id":"1309.6821","version":1},"attestation_state":"computed","paper":{"title":"Sample Complexity of Multi-task Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emma Brunskill, Lihong Li","submitted_at":"2013-09-26T12:36:00Z","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"},"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":"1309.6821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-09-26T12:36:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e753e532f684ec6c98b171510a84b765751282d6cedc05f67b65f4146198ce3f","abstract_canon_sha256":"06c753377824eaf3492e5189b259c791dda8df10ae1ed52bec30a6f9474ed14b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:12:10.340358Z","signature_b64":"2EBU9At1ktupa/ZEGv4bzzu8GSauK8Dk3nCzMxZXd4dpZa8avI+2y90WJ6fqx43uyVFiCi1KiMmMqPE+Ap1wCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ac19947bec41e6d27162ce2d79206b5a35ca72fb7e2451e66f827216b5bfad4","last_reissued_at":"2026-05-18T03:12:10.339490Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:12:10.339490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample Complexity of Multi-task Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emma Brunskill, Lihong Li","submitted_at":"2013-09-26T12:36:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1309.6821","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":""},"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":"1309.6821","created_at":"2026-05-18T03:12:10.339630+00:00"},{"alias_kind":"arxiv_version","alias_value":"1309.6821v1","created_at":"2026-05-18T03:12:10.339630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1309.6821","created_at":"2026-05-18T03:12:10.339630+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLAZSR56YQPG","created_at":"2026-05-18T12:27:52.871228+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLAZSR56YQPG2JYW","created_at":"2026-05-18T12:27:52.871228+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLAZSR56","created_at":"2026-05-18T12:27:52.871228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":298,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03891","citing_title":"Provable Multi-Task Reinforcement Learning: A Representation Learning Framework with Low Rank Rewards","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLAZSR56YQPG2JYWFTRNPEQGWW","json":"https://pith.science/pith/NLAZSR56YQPG2JYWFTRNPEQGWW.json","graph_json":"https://pith.science/api/pith-number/NLAZSR56YQPG2JYWFTRNPEQGWW/graph.json","events_json":"https://pith.science/api/pith-number/NLAZSR56YQPG2JYWFTRNPEQGWW/events.json","paper":"https://pith.science/paper/NLAZSR56"},"agent_actions":{"view_html":"https://pith.science/pith/NLAZSR56YQPG2JYWFTRNPEQGWW","download_json":"https://pith.science/pith/NLAZSR56YQPG2JYWFTRNPEQGWW.json","view_paper":"https://pith.science/paper/NLAZSR56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1309.6821&json=true","fetch_graph":"https://pith.science/api/pith-number/NLAZSR56YQPG2JYWFTRNPEQGWW/graph.json","fetch_events":"https://pith.science/api/pith-number/NLAZSR56YQPG2JYWFTRNPEQGWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLAZSR56YQPG2JYWFTRNPEQGWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLAZSR56YQPG2JYWFTRNPEQGWW/action/storage_attestation","attest_author":"https://pith.science/pith/NLAZSR56YQPG2JYWFTRNPEQGWW/action/author_attestation","sign_citation":"https://pith.science/pith/NLAZSR56YQPG2JYWFTRNPEQGWW/action/citation_signature","submit_replication":"https://pith.science/pith/NLAZSR56YQPG2JYWFTRNPEQGWW/action/replication_record"}},"created_at":"2026-05-18T03:12:10.339630+00:00","updated_at":"2026-05-18T03:12:10.339630+00:00"}