{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3JZL5VAG4KZF65UYYPBXPVW7SO","short_pith_number":"pith:3JZL5VAG","schema_version":"1.0","canonical_sha256":"da72bed406e2b25f7698c3c377d6df93af32172442d2358b642874b4abb28c45","source":{"kind":"arxiv","id":"2410.10737","version":2},"attestation_state":"computed","paper":{"title":"Asymptotic Analysis of Sample-averaged Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ruiqi Liu, Saunak Kumar Panda, Yisha Xiang","submitted_at":"2024-10-14T17:17:19Z","abstract_excerpt":"Reinforcement learning (RL) has emerged as a key approach for training agents in complex and uncertain environments. Incorporating statistical inference in RL algorithms is essential for understanding and managing uncertainty in model performance. This paper introduces a generalized framework for time-varying batch-averaged Q-learning, termed sample-averaged Q-learning (SA-QL), which extends traditional single-sample Q-learning by aggregating samples of rewards and next states to better account for data variability and uncertainty. We leverage the functional central limit theorem (FCLT) to est"},"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":"2410.10737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T17:17:19Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"7990803872392b0193aadafcd5a6fb992a3d88e07f1aefbf276d7c829db62f54","abstract_canon_sha256":"1e5032d4ddd80ef5d7718746f5b3be34ff39aafb7451fb876b7299e6357034f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:40.574267Z","signature_b64":"S/s0rslrbnjtWaWgTY/ULyDmUTRWGhEc4SzRhW042iJys+yhLD2gwB1qpZyxTGemPSl4VZLKK0gxBneOS85qCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da72bed406e2b25f7698c3c377d6df93af32172442d2358b642874b4abb28c45","last_reissued_at":"2026-07-05T10:20:40.573651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:40.573651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymptotic Analysis of Sample-averaged Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ruiqi Liu, Saunak Kumar Panda, Yisha Xiang","submitted_at":"2024-10-14T17:17:19Z","abstract_excerpt":"Reinforcement learning (RL) has emerged as a key approach for training agents in complex and uncertain environments. Incorporating statistical inference in RL algorithms is essential for understanding and managing uncertainty in model performance. This paper introduces a generalized framework for time-varying batch-averaged Q-learning, termed sample-averaged Q-learning (SA-QL), which extends traditional single-sample Q-learning by aggregating samples of rewards and next states to better account for data variability and uncertainty. We leverage the functional central limit theorem (FCLT) to est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10737","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/2410.10737/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":"2410.10737","created_at":"2026-07-05T10:20:40.573726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10737v2","created_at":"2026-07-05T10:20:40.573726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10737","created_at":"2026-07-05T10:20:40.573726+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JZL5VAG4KZF","created_at":"2026-07-05T10:20:40.573726+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JZL5VAG4KZF65UY","created_at":"2026-07-05T10:20:40.573726+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JZL5VAG","created_at":"2026-07-05T10:20:40.573726+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/3JZL5VAG4KZF65UYYPBXPVW7SO","json":"https://pith.science/pith/3JZL5VAG4KZF65UYYPBXPVW7SO.json","graph_json":"https://pith.science/api/pith-number/3JZL5VAG4KZF65UYYPBXPVW7SO/graph.json","events_json":"https://pith.science/api/pith-number/3JZL5VAG4KZF65UYYPBXPVW7SO/events.json","paper":"https://pith.science/paper/3JZL5VAG"},"agent_actions":{"view_html":"https://pith.science/pith/3JZL5VAG4KZF65UYYPBXPVW7SO","download_json":"https://pith.science/pith/3JZL5VAG4KZF65UYYPBXPVW7SO.json","view_paper":"https://pith.science/paper/3JZL5VAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10737&json=true","fetch_graph":"https://pith.science/api/pith-number/3JZL5VAG4KZF65UYYPBXPVW7SO/graph.json","fetch_events":"https://pith.science/api/pith-number/3JZL5VAG4KZF65UYYPBXPVW7SO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JZL5VAG4KZF65UYYPBXPVW7SO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JZL5VAG4KZF65UYYPBXPVW7SO/action/storage_attestation","attest_author":"https://pith.science/pith/3JZL5VAG4KZF65UYYPBXPVW7SO/action/author_attestation","sign_citation":"https://pith.science/pith/3JZL5VAG4KZF65UYYPBXPVW7SO/action/citation_signature","submit_replication":"https://pith.science/pith/3JZL5VAG4KZF65UYYPBXPVW7SO/action/replication_record"}},"created_at":"2026-07-05T10:20:40.573726+00:00","updated_at":"2026-07-05T10:20:40.573726+00:00"}