{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QTTXG7EXDO4B3XJDHAPSFPSOSS","short_pith_number":"pith:QTTXG7EX","schema_version":"1.0","canonical_sha256":"84e7737c971bb81ddd23381f22be4e948c3fee4df9efd581b24cf8dfcf7e57a6","source":{"kind":"arxiv","id":"1506.03379","version":2},"attestation_state":"computed","paper":{"title":"The Online Coupon-Collector Problem and Its Application to Lifelong Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emma Brunskill, Lihong Li","submitted_at":"2015-06-10T16:23:29Z","abstract_excerpt":"Transferring knowledge across a sequence of related tasks is an important challenge in reinforcement learning (RL). Despite much encouraging empirical evidence, there has been little theoretical analysis. In this paper, we study a class of lifelong RL problems: the agent solves a sequence of tasks modeled as finite Markov decision processes (MDPs), each of which is from a finite set of MDPs with the same state/action sets and different transition/reward functions. Motivated by the need for cross-task exploration in lifelong learning, we formulate a novel online coupon-collector problem and giv"},"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":"1506.03379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T16:23:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f9175720b713d871ad07f391fe055c2242501fd50c776570d13a2652c66039a","abstract_canon_sha256":"b3654843082d11d2306e1bd8a28f5d0d3d21a8f4a7f936c69ee520f66399ddd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:29.174878Z","signature_b64":"asp7CHjPf4oW8G4m3CFXzoUb+K382kKiZEMk9PcIBg8EnWCxc2daFvk4cYYethcFXo2hddQyvAACGrkgnt3+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84e7737c971bb81ddd23381f22be4e948c3fee4df9efd581b24cf8dfcf7e57a6","last_reissued_at":"2026-05-18T01:32:29.174368Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:29.174368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Online Coupon-Collector Problem and Its Application to Lifelong Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emma Brunskill, Lihong Li","submitted_at":"2015-06-10T16:23:29Z","abstract_excerpt":"Transferring knowledge across a sequence of related tasks is an important challenge in reinforcement learning (RL). Despite much encouraging empirical evidence, there has been little theoretical analysis. In this paper, we study a class of lifelong RL problems: the agent solves a sequence of tasks modeled as finite Markov decision processes (MDPs), each of which is from a finite set of MDPs with the same state/action sets and different transition/reward functions. Motivated by the need for cross-task exploration in lifelong learning, we formulate a novel online coupon-collector problem and giv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03379","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":"1506.03379","created_at":"2026-05-18T01:32:29.174442+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.03379v2","created_at":"2026-05-18T01:32:29.174442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03379","created_at":"2026-05-18T01:32:29.174442+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTTXG7EXDO4B","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTTXG7EXDO4B3XJD","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTTXG7EX","created_at":"2026-05-18T12:29:39.896362+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/QTTXG7EXDO4B3XJDHAPSFPSOSS","json":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS.json","graph_json":"https://pith.science/api/pith-number/QTTXG7EXDO4B3XJDHAPSFPSOSS/graph.json","events_json":"https://pith.science/api/pith-number/QTTXG7EXDO4B3XJDHAPSFPSOSS/events.json","paper":"https://pith.science/paper/QTTXG7EX"},"agent_actions":{"view_html":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS","download_json":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS.json","view_paper":"https://pith.science/paper/QTTXG7EX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.03379&json=true","fetch_graph":"https://pith.science/api/pith-number/QTTXG7EXDO4B3XJDHAPSFPSOSS/graph.json","fetch_events":"https://pith.science/api/pith-number/QTTXG7EXDO4B3XJDHAPSFPSOSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/action/storage_attestation","attest_author":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/action/author_attestation","sign_citation":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/action/citation_signature","submit_replication":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/action/replication_record"}},"created_at":"2026-05-18T01:32:29.174442+00:00","updated_at":"2026-05-18T01:32:29.174442+00:00"}