{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TTRR3M3GNPWHVVLUGXJ44YKA4U","short_pith_number":"pith:TTRR3M3G","schema_version":"1.0","canonical_sha256":"9ce31db3666bec7ad57435d3ce6140e517fd33befb89bcb2cf5c55925485c60c","source":{"kind":"arxiv","id":"1904.11439","version":6},"attestation_state":"computed","paper":{"title":"META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Ian Porada, Mingde Zhao, Sitao Luan, Xiao-Wen Chang","submitted_at":"2019-04-25T16:32:21Z","abstract_excerpt":"Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies. TD-learning with eligibility traces provides a way to boost sample efficiency by temporal credit assignment, i.e. deciding which portion of a reward should be assigned to predecessor states that occurred at different previous times, controlled by a parameter $\\lambda$. However, tuning this parameter can be time-consuming, and not tuning it can lead to inefficient lea"},"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":"1904.11439","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-25T16:32:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"38deab8982dc893f4f795de35c09d7c1826b9ef3fedde4ec69b1f848dc4b6fe7","abstract_canon_sha256":"c3b3046367c358abb8bb981d0aa97d0b36dce82fd1ba3818837a7866e96a5837"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:19.154872Z","signature_b64":"QLa3K6H6YG2rV/4gfQmoG8fRmFtWzk/3YIlaGOQonhYEd3JieYdS6C4XcuQgBJw7A76fOzJb+odRE/63KM6FAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ce31db3666bec7ad57435d3ce6140e517fd33befb89bcb2cf5c55925485c60c","last_reissued_at":"2026-07-05T01:03:19.154431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:19.154431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Ian Porada, Mingde Zhao, Sitao Luan, Xiao-Wen Chang","submitted_at":"2019-04-25T16:32:21Z","abstract_excerpt":"Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies. TD-learning with eligibility traces provides a way to boost sample efficiency by temporal credit assignment, i.e. deciding which portion of a reward should be assigned to predecessor states that occurred at different previous times, controlled by a parameter $\\lambda$. However, tuning this parameter can be time-consuming, and not tuning it can lead to inefficient lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11439","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1904.11439/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1904.11439","created_at":"2026-07-05T01:03:19.154494+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.11439v6","created_at":"2026-07-05T01:03:19.154494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11439","created_at":"2026-07-05T01:03:19.154494+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTRR3M3GNPWH","created_at":"2026-07-05T01:03:19.154494+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTRR3M3GNPWHVVLU","created_at":"2026-07-05T01:03:19.154494+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTRR3M3G","created_at":"2026-07-05T01:03:19.154494+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/TTRR3M3GNPWHVVLUGXJ44YKA4U","json":"https://pith.science/pith/TTRR3M3GNPWHVVLUGXJ44YKA4U.json","graph_json":"https://pith.science/api/pith-number/TTRR3M3GNPWHVVLUGXJ44YKA4U/graph.json","events_json":"https://pith.science/api/pith-number/TTRR3M3GNPWHVVLUGXJ44YKA4U/events.json","paper":"https://pith.science/paper/TTRR3M3G"},"agent_actions":{"view_html":"https://pith.science/pith/TTRR3M3GNPWHVVLUGXJ44YKA4U","download_json":"https://pith.science/pith/TTRR3M3GNPWHVVLUGXJ44YKA4U.json","view_paper":"https://pith.science/paper/TTRR3M3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.11439&json=true","fetch_graph":"https://pith.science/api/pith-number/TTRR3M3GNPWHVVLUGXJ44YKA4U/graph.json","fetch_events":"https://pith.science/api/pith-number/TTRR3M3GNPWHVVLUGXJ44YKA4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTRR3M3GNPWHVVLUGXJ44YKA4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTRR3M3GNPWHVVLUGXJ44YKA4U/action/storage_attestation","attest_author":"https://pith.science/pith/TTRR3M3GNPWHVVLUGXJ44YKA4U/action/author_attestation","sign_citation":"https://pith.science/pith/TTRR3M3GNPWHVVLUGXJ44YKA4U/action/citation_signature","submit_replication":"https://pith.science/pith/TTRR3M3GNPWHVVLUGXJ44YKA4U/action/replication_record"}},"created_at":"2026-07-05T01:03:19.154494+00:00","updated_at":"2026-07-05T01:03:19.154494+00:00"}