{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6SZWATWXADYN5I6ODTSKFEXDDU","short_pith_number":"pith:6SZWATWX","schema_version":"1.0","canonical_sha256":"f4b3604ed700f0dea3ce1ce4a292e31d3fa80a91f323798788e96055efffc365","source":{"kind":"arxiv","id":"2506.07040","version":4},"attestation_state":"computed","paper":{"title":"Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Swetha Ganesh, Vaneet Aggarwal, Yang Xu","submitted_at":"2025-06-08T08:26:27Z","abstract_excerpt":"We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs). We present non-asymptotic convergence analyses of Q-learning and actor-critic algorithms for robust average-reward MDPs under contamination, total-variation distance, and Wasserstein uncertainty sets. A key ingredient of our analysis is showing that the optimal robust Bellman operator is a strict contraction with respect to a carefully designed semi-norm. This property enables a stochastic approximation update that learns the optimal robust $Q$-function with $\\tilde{\\mathca"},"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":"2506.07040","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-08T08:26:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"307efb1d672774fc5294eded69349723c5197cfa72366a00b557a5838892fb1d","abstract_canon_sha256":"1fed25d88f7b6099685c81d3294c17899c5c42379689033d72b4857558bc90cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:59.598647Z","signature_b64":"PHzLeJzsB5tBHVX2eU66IILNGyoghMTExN+Jl+YHZMhSNnoTXN9T6KnJcvX7CdNmh6yLGVy9qGgNcdZzbfhBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4b3604ed700f0dea3ce1ce4a292e31d3fa80a91f323798788e96055efffc365","last_reissued_at":"2026-07-14T01:21:59.597713Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:59.597713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Swetha Ganesh, Vaneet Aggarwal, Yang Xu","submitted_at":"2025-06-08T08:26:27Z","abstract_excerpt":"We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs). We present non-asymptotic convergence analyses of Q-learning and actor-critic algorithms for robust average-reward MDPs under contamination, total-variation distance, and Wasserstein uncertainty sets. A key ingredient of our analysis is showing that the optimal robust Bellman operator is a strict contraction with respect to a carefully designed semi-norm. This property enables a stochastic approximation update that learns the optimal robust $Q$-function with $\\tilde{\\mathca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07040","kind":"arxiv","version":4},"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/2506.07040/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":"2506.07040","created_at":"2026-07-14T01:21:59.598160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07040v4","created_at":"2026-07-14T01:21:59.598160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07040","created_at":"2026-07-14T01:21:59.598160+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SZWATWXADYN","created_at":"2026-07-14T01:21:59.598160+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SZWATWXADYN5I6O","created_at":"2026-07-14T01:21:59.598160+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SZWATWX","created_at":"2026-07-14T01:21:59.598160+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/6SZWATWXADYN5I6ODTSKFEXDDU","json":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU.json","graph_json":"https://pith.science/api/pith-number/6SZWATWXADYN5I6ODTSKFEXDDU/graph.json","events_json":"https://pith.science/api/pith-number/6SZWATWXADYN5I6ODTSKFEXDDU/events.json","paper":"https://pith.science/paper/6SZWATWX"},"agent_actions":{"view_html":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU","download_json":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU.json","view_paper":"https://pith.science/paper/6SZWATWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07040&json=true","fetch_graph":"https://pith.science/api/pith-number/6SZWATWXADYN5I6ODTSKFEXDDU/graph.json","fetch_events":"https://pith.science/api/pith-number/6SZWATWXADYN5I6ODTSKFEXDDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU/action/storage_attestation","attest_author":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU/action/author_attestation","sign_citation":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU/action/citation_signature","submit_replication":"https://pith.science/pith/6SZWATWXADYN5I6ODTSKFEXDDU/action/replication_record"}},"created_at":"2026-07-14T01:21:59.598160+00:00","updated_at":"2026-07-14T01:21:59.598160+00:00"}