{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E6XXOR2PJSNP54STQSWSS6IMUH","short_pith_number":"pith:E6XXOR2P","schema_version":"1.0","canonical_sha256":"27af77474f4c9afef25384ad29790ca1e77603838e158bfd2a5aaa0adba7adcf","source":{"kind":"arxiv","id":"2402.15781","version":2},"attestation_state":"computed","paper":{"title":"Analysis of Off-Policy Multi-Step TD-Learning with Linear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Donghwan Lee","submitted_at":"2024-02-24T10:42:50Z","abstract_excerpt":"This paper analyzes multi-step TD-learning algorithms within the `deadly triad' scenario, characterized by linear function approximation, off-policy learning, and bootstrapping. In particular, we prove that n-step TD-learning algorithms converge to a solution as the sampling horizon n increases sufficiently. The paper is divided into two parts. In the first part, we comprehensively examine the fundamental properties of their model-based deterministic counterparts, including projected value iteration, gradient descent algorithms, and the control theoretic approach, which can be viewed as protot"},"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":"2402.15781","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-02-24T10:42:50Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"8afa12b2c537391e4d1fc1af00930c19f5dc6ececf7f4afb479698a233e960ca","abstract_canon_sha256":"bdfbd34cb4bcf718ab97e6b8a5f552e37427232ad0ef05a361ca31825a195422"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:39.656569Z","signature_b64":"VIeW+pC8TqrT+ryobNsx6BgA9eHiTtvwCLEPjO2aNVUikM/LDGzYdz93Twisu1eXmPXyzPdZbyqmiFP995J4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27af77474f4c9afef25384ad29790ca1e77603838e158bfd2a5aaa0adba7adcf","last_reissued_at":"2026-07-05T08:05:39.655918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:39.655918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis of Off-Policy Multi-Step TD-Learning with Linear Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Donghwan Lee","submitted_at":"2024-02-24T10:42:50Z","abstract_excerpt":"This paper analyzes multi-step TD-learning algorithms within the `deadly triad' scenario, characterized by linear function approximation, off-policy learning, and bootstrapping. In particular, we prove that n-step TD-learning algorithms converge to a solution as the sampling horizon n increases sufficiently. The paper is divided into two parts. In the first part, we comprehensively examine the fundamental properties of their model-based deterministic counterparts, including projected value iteration, gradient descent algorithms, and the control theoretic approach, which can be viewed as protot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15781","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.15781/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":"2402.15781","created_at":"2026-07-05T08:05:39.656006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15781v2","created_at":"2026-07-05T08:05:39.656006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15781","created_at":"2026-07-05T08:05:39.656006+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6XXOR2PJSNP","created_at":"2026-07-05T08:05:39.656006+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6XXOR2PJSNP54ST","created_at":"2026-07-05T08:05:39.656006+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6XXOR2P","created_at":"2026-07-05T08:05:39.656006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18892","citing_title":"A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges","ref_index":96,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6XXOR2PJSNP54STQSWSS6IMUH","json":"https://pith.science/pith/E6XXOR2PJSNP54STQSWSS6IMUH.json","graph_json":"https://pith.science/api/pith-number/E6XXOR2PJSNP54STQSWSS6IMUH/graph.json","events_json":"https://pith.science/api/pith-number/E6XXOR2PJSNP54STQSWSS6IMUH/events.json","paper":"https://pith.science/paper/E6XXOR2P"},"agent_actions":{"view_html":"https://pith.science/pith/E6XXOR2PJSNP54STQSWSS6IMUH","download_json":"https://pith.science/pith/E6XXOR2PJSNP54STQSWSS6IMUH.json","view_paper":"https://pith.science/paper/E6XXOR2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15781&json=true","fetch_graph":"https://pith.science/api/pith-number/E6XXOR2PJSNP54STQSWSS6IMUH/graph.json","fetch_events":"https://pith.science/api/pith-number/E6XXOR2PJSNP54STQSWSS6IMUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6XXOR2PJSNP54STQSWSS6IMUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6XXOR2PJSNP54STQSWSS6IMUH/action/storage_attestation","attest_author":"https://pith.science/pith/E6XXOR2PJSNP54STQSWSS6IMUH/action/author_attestation","sign_citation":"https://pith.science/pith/E6XXOR2PJSNP54STQSWSS6IMUH/action/citation_signature","submit_replication":"https://pith.science/pith/E6XXOR2PJSNP54STQSWSS6IMUH/action/replication_record"}},"created_at":"2026-07-05T08:05:39.656006+00:00","updated_at":"2026-07-05T08:05:39.656006+00:00"}