{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3JZL5VAG4KZF65UYYPBXPVW7SO","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":"1e5032d4ddd80ef5d7718746f5b3be34ff39aafb7451fb876b7299e6357034f8","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T17:17:19Z","title_canon_sha256":"7990803872392b0193aadafcd5a6fb992a3d88e07f1aefbf276d7c829db62f54"},"schema_version":"1.0","source":{"id":"2410.10737","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10737","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10737v2","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10737","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"3JZL5VAG4KZF","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"3JZL5VAG4KZF65UY","created_at":"2026-07-05T10:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"3JZL5VAG","created_at":"2026-07-05T10:20:40Z"}],"graph_snapshots":[{"event_id":"sha256:e903acd76aa894e306cca914860f3b6e1125a878f513998bbcc19ff4eb18158a","target":"graph","created_at":"2026-07-05T10:20:40Z","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/2410.10737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ruiqi Liu, Saunak Kumar Panda, Yisha Xiang","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T17:17:19Z","title":"Asymptotic Analysis of Sample-averaged Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10737","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":"sha256:1dcdc5bc5b7a869e6a1376e651cb0fa8acdc8ee5e090d963dcf61c041b4c2161","target":"record","created_at":"2026-07-05T10:20:40Z","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":"1e5032d4ddd80ef5d7718746f5b3be34ff39aafb7451fb876b7299e6357034f8","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T17:17:19Z","title_canon_sha256":"7990803872392b0193aadafcd5a6fb992a3d88e07f1aefbf276d7c829db62f54"},"schema_version":"1.0","source":{"id":"2410.10737","kind":"arxiv","version":2}},"canonical_sha256":"da72bed406e2b25f7698c3c377d6df93af32172442d2358b642874b4abb28c45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da72bed406e2b25f7698c3c377d6df93af32172442d2358b642874b4abb28c45","first_computed_at":"2026-07-05T10:20:40.573651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:40.573651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S/s0rslrbnjtWaWgTY/ULyDmUTRWGhEc4SzRhW042iJys+yhLD2gwB1qpZyxTGemPSl4VZLKK0gxBneOS85qCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:40.574267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10737","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dcdc5bc5b7a869e6a1376e651cb0fa8acdc8ee5e090d963dcf61c041b4c2161","sha256:e903acd76aa894e306cca914860f3b6e1125a878f513998bbcc19ff4eb18158a"],"state_sha256":"d108d4b73ffc3ad2431395a53313a852d2c5aa40b8852da3fe1faedcab120ca8"}