{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E6XXOR2PJSNP54STQSWSS6IMUH","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":"bdfbd34cb4bcf718ab97e6b8a5f552e37427232ad0ef05a361ca31825a195422","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-02-24T10:42:50Z","title_canon_sha256":"8afa12b2c537391e4d1fc1af00930c19f5dc6ececf7f4afb479698a233e960ca"},"schema_version":"1.0","source":{"id":"2402.15781","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15781","created_at":"2026-07-05T08:05:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15781v2","created_at":"2026-07-05T08:05:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15781","created_at":"2026-07-05T08:05:39Z"},{"alias_kind":"pith_short_12","alias_value":"E6XXOR2PJSNP","created_at":"2026-07-05T08:05:39Z"},{"alias_kind":"pith_short_16","alias_value":"E6XXOR2PJSNP54ST","created_at":"2026-07-05T08:05:39Z"},{"alias_kind":"pith_short_8","alias_value":"E6XXOR2P","created_at":"2026-07-05T08:05:39Z"}],"graph_snapshots":[{"event_id":"sha256:dc71b3033595ee191e8e1399352c7d861d032c329ca189cc787aa20dd2aadb22","target":"graph","created_at":"2026-07-05T08:05:39Z","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/2402.15781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Donghwan Lee","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-02-24T10:42:50Z","title":"Analysis of Off-Policy Multi-Step TD-Learning with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15781","kind":"arxiv","version":2},"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:bb55843817789acec775a3d84369308ce0ce7dcd14e80c7d38f62e2f0c285d77","target":"record","created_at":"2026-07-05T08:05:39Z","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":"bdfbd34cb4bcf718ab97e6b8a5f552e37427232ad0ef05a361ca31825a195422","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-02-24T10:42:50Z","title_canon_sha256":"8afa12b2c537391e4d1fc1af00930c19f5dc6ececf7f4afb479698a233e960ca"},"schema_version":"1.0","source":{"id":"2402.15781","kind":"arxiv","version":2}},"canonical_sha256":"27af77474f4c9afef25384ad29790ca1e77603838e158bfd2a5aaa0adba7adcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27af77474f4c9afef25384ad29790ca1e77603838e158bfd2a5aaa0adba7adcf","first_computed_at":"2026-07-05T08:05:39.655918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:39.655918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VIeW+pC8TqrT+ryobNsx6BgA9eHiTtvwCLEPjO2aNVUikM/LDGzYdz93Twisu1eXmPXyzPdZbyqmiFP995J4BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:39.656569Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15781","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb55843817789acec775a3d84369308ce0ce7dcd14e80c7d38f62e2f0c285d77","sha256:dc71b3033595ee191e8e1399352c7d861d032c329ca189cc787aa20dd2aadb22"],"state_sha256":"9fc3c59ac687a55573e2c6d063d3bced500c75d1e2c9173a2e13e5152b7b81fe"}