{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TTRR3M3GNPWHVVLUGXJ44YKA4U","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":"c3b3046367c358abb8bb981d0aa97d0b36dce82fd1ba3818837a7866e96a5837","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-25T16:32:21Z","title_canon_sha256":"38deab8982dc893f4f795de35c09d7c1826b9ef3fedde4ec69b1f848dc4b6fe7"},"schema_version":"1.0","source":{"id":"1904.11439","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11439","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11439v6","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11439","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"TTRR3M3GNPWH","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"TTRR3M3GNPWHVVLU","created_at":"2026-07-05T01:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"TTRR3M3G","created_at":"2026-07-05T01:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:3c6633d9879cd28cd24af845a6f9fde89503e7cbec66073a2df7870ce7a4a119","target":"graph","created_at":"2026-07-05T01:03:19Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1904.11439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Doina Precup, Ian Porada, Mingde Zhao, Sitao Luan, Xiao-Wen Chang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-25T16:32:21Z","title":"META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11439","kind":"arxiv","version":6},"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":"sha256:45cc4c9a45796e332e91fe53c559bfe87304d7c6690d7775e5b53ce729f1de80","target":"record","created_at":"2026-07-05T01:03:19Z","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":"c3b3046367c358abb8bb981d0aa97d0b36dce82fd1ba3818837a7866e96a5837","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-25T16:32:21Z","title_canon_sha256":"38deab8982dc893f4f795de35c09d7c1826b9ef3fedde4ec69b1f848dc4b6fe7"},"schema_version":"1.0","source":{"id":"1904.11439","kind":"arxiv","version":6}},"canonical_sha256":"9ce31db3666bec7ad57435d3ce6140e517fd33befb89bcb2cf5c55925485c60c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ce31db3666bec7ad57435d3ce6140e517fd33befb89bcb2cf5c55925485c60c","first_computed_at":"2026-07-05T01:03:19.154431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:03:19.154431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QLa3K6H6YG2rV/4gfQmoG8fRmFtWzk/3YIlaGOQonhYEd3JieYdS6C4XcuQgBJw7A76fOzJb+odRE/63KM6FAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:03:19.154872Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.11439","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45cc4c9a45796e332e91fe53c559bfe87304d7c6690d7775e5b53ce729f1de80","sha256:3c6633d9879cd28cd24af845a6f9fde89503e7cbec66073a2df7870ce7a4a119"],"state_sha256":"e8dbefe02f2d65e2f15f0c62e6c0ac2fb31d4373ad1c7fb8233c91dce8a48ea3"}