{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4IXMM3LGXQT7QHWT23LNGXBWVE","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":"1acc72e398a0f3919f79b1408f0f2823f70937355d6ef6c7cc7a86eb72870113","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T15:34:45Z","title_canon_sha256":"972691b02cc1d33deaa10834e9cd5ed1081b3643aea06a25763b63a379d0866a"},"schema_version":"1.0","source":{"id":"2505.12462","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12462","created_at":"2026-06-23T02:13:15Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12462v3","created_at":"2026-06-23T02:13:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12462","created_at":"2026-06-23T02:13:15Z"},{"alias_kind":"pith_short_12","alias_value":"4IXMM3LGXQT7","created_at":"2026-06-23T02:13:15Z"},{"alias_kind":"pith_short_16","alias_value":"4IXMM3LGXQT7QHWT","created_at":"2026-06-23T02:13:15Z"},{"alias_kind":"pith_short_8","alias_value":"4IXMM3LG","created_at":"2026-06-23T02:13:15Z"}],"graph_snapshots":[{"event_id":"sha256:41b1e990b6c5b7d617c7fca7145afc0b4d3177a98b0dca913c77868b6f5f1350","target":"graph","created_at":"2026-06-23T02:13:15Z","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/2505.12462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust reinforcement learning (RL) under the average-reward criterion is essential for long-term decision-making, particularly when the environment may differ from its training dynamics. However, most existing studies focus on model-based settings and provide only asymptotic guarantees, hindering their principled understanding and practical deployment, especially in data-limited scenarios. We aim to close this gap by proposing a model-free algorithm, \\textbf{Robust Halpern Iteration (RHI)}. We first design our algorithm based on a black-box sampling oracle, which can estimate the worst-case pe","authors_text":"George Atia, Yue Wang, Zachary Roch","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T15:34:45Z","title":"Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12462","kind":"arxiv","version":3},"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":"sha256:15dc28ce0943d7c643b967a89181bf74dd5a0dce41466af354e1128a88c626c4","target":"record","created_at":"2026-06-23T02:13:15Z","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":"1acc72e398a0f3919f79b1408f0f2823f70937355d6ef6c7cc7a86eb72870113","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T15:34:45Z","title_canon_sha256":"972691b02cc1d33deaa10834e9cd5ed1081b3643aea06a25763b63a379d0866a"},"schema_version":"1.0","source":{"id":"2505.12462","kind":"arxiv","version":3}},"canonical_sha256":"e22ec66d66bc27f81ed3d6d6d35c36a93144991974ded528f1b21767ff10ca90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e22ec66d66bc27f81ed3d6d6d35c36a93144991974ded528f1b21767ff10ca90","first_computed_at":"2026-06-23T02:13:15.305321Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:15.305321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o/pwYFz4awc5rzt+S8naj83QtDt83odY8cxyGLW7yfB+cfyAaaiD9tY5mhYYQFhab1cUmeNo8oDNEfH7Upj1Bg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:15.305742Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12462","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15dc28ce0943d7c643b967a89181bf74dd5a0dce41466af354e1128a88c626c4","sha256:41b1e990b6c5b7d617c7fca7145afc0b4d3177a98b0dca913c77868b6f5f1350"],"state_sha256":"a95ce11506b12cec35f6efb7073dc30d11d09e26c0bf900102a85dca9f2eedb3"}