{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JYNFBQ5WS4OO6KDFKX5AVDIUYD","short_pith_number":"pith:JYNFBQ5W","schema_version":"1.0","canonical_sha256":"4e1a50c3b6971cef286555fa0a8d14c0c99ed43271277b67810c8236ba8eecda","source":{"kind":"arxiv","id":"2509.08933","version":2},"attestation_state":"computed","paper":{"title":"Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra, Sreejeet Maity","submitted_at":"2025-09-10T18:56:39Z","abstract_excerpt":"We study the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting in the presence of adversarially corrupted rewards. To address this problem, we develop a novel robust variant of the \\(Q\\)-learning algorithm and analyze it under the challenging asynchronous sampling model with time-correlated data. Despite corruption, we prove that the finite-time guarantees of our approach match existing bounds, up to an additive term that scales with the fraction of corrupted samples. We also establish an information-theoretic lower bound, revealing th"},"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":"2509.08933","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T18:56:39Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"aa2371392950a38a029f7f98bafc6cbeccce59aac0df1cf25bd0107be3a565a1","abstract_canon_sha256":"005f7061a9180227ce65e340023ff2473c71a6ca1a524449b1c46f03735ed9d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:36.888981Z","signature_b64":"18jNc3jzR8a7LERNZzieScbjWEIrlzsaRyl6g7rjDcoKccdgXOsc6i1jUpZKZi1Kg/LcElCHgnvDQn+DJwkEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e1a50c3b6971cef286555fa0a8d14c0c99ed43271277b67810c8236ba8eecda","last_reissued_at":"2026-05-22T02:04:36.887949Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:36.887949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra, Sreejeet Maity","submitted_at":"2025-09-10T18:56:39Z","abstract_excerpt":"We study the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting in the presence of adversarially corrupted rewards. To address this problem, we develop a novel robust variant of the \\(Q\\)-learning algorithm and analyze it under the challenging asynchronous sampling model with time-correlated data. Despite corruption, we prove that the finite-time guarantees of our approach match existing bounds, up to an additive term that scales with the fraction of corrupted samples. We also establish an information-theoretic lower bound, revealing th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08933","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/2509.08933/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":"2509.08933","created_at":"2026-05-22T02:04:36.888117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08933v2","created_at":"2026-05-22T02:04:36.888117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08933","created_at":"2026-05-22T02:04:36.888117+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYNFBQ5WS4OO","created_at":"2026-05-22T02:04:36.888117+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYNFBQ5WS4OO6KDF","created_at":"2026-05-22T02:04:36.888117+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYNFBQ5W","created_at":"2026-05-22T02:04:36.888117+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/JYNFBQ5WS4OO6KDFKX5AVDIUYD","json":"https://pith.science/pith/JYNFBQ5WS4OO6KDFKX5AVDIUYD.json","graph_json":"https://pith.science/api/pith-number/JYNFBQ5WS4OO6KDFKX5AVDIUYD/graph.json","events_json":"https://pith.science/api/pith-number/JYNFBQ5WS4OO6KDFKX5AVDIUYD/events.json","paper":"https://pith.science/paper/JYNFBQ5W"},"agent_actions":{"view_html":"https://pith.science/pith/JYNFBQ5WS4OO6KDFKX5AVDIUYD","download_json":"https://pith.science/pith/JYNFBQ5WS4OO6KDFKX5AVDIUYD.json","view_paper":"https://pith.science/paper/JYNFBQ5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08933&json=true","fetch_graph":"https://pith.science/api/pith-number/JYNFBQ5WS4OO6KDFKX5AVDIUYD/graph.json","fetch_events":"https://pith.science/api/pith-number/JYNFBQ5WS4OO6KDFKX5AVDIUYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYNFBQ5WS4OO6KDFKX5AVDIUYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYNFBQ5WS4OO6KDFKX5AVDIUYD/action/storage_attestation","attest_author":"https://pith.science/pith/JYNFBQ5WS4OO6KDFKX5AVDIUYD/action/author_attestation","sign_citation":"https://pith.science/pith/JYNFBQ5WS4OO6KDFKX5AVDIUYD/action/citation_signature","submit_replication":"https://pith.science/pith/JYNFBQ5WS4OO6KDFKX5AVDIUYD/action/replication_record"}},"created_at":"2026-05-22T02:04:36.888117+00:00","updated_at":"2026-05-22T02:04:36.888117+00:00"}