{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U5PX7LEMBZ4JBDCBBQZ5VQ2YCK","short_pith_number":"pith:U5PX7LEM","schema_version":"1.0","canonical_sha256":"a75f7fac8c0e78908c410c33dac358129425e3007bdf9fd9a5982ffc0ca51639","source":{"kind":"arxiv","id":"2405.17882","version":2},"attestation_state":"computed","paper":{"title":"Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","math.PR"],"primary_cat":"cs.LG","authors_text":"Qiaomin Xie, Weina Wang, Yige Hong, Yudong Chen","submitted_at":"2024-05-28T07:08:29Z","abstract_excerpt":"We consider the infinite-horizon average-reward restless bandit problem. We propose a novel \\emph{two-set policy} that maintains two dynamic subsets of arms: one subset of arms has a nearly optimal state distribution and takes actions according to an Optimal Local Control routine; the other subset of arms is driven towards the optimal state distribution and gradually merged into the first subset. We show that our two-set policy is asymptotically optimal with an $O(\\exp(-C N))$ optimality gap for an $N$-armed problem, under the mild assumptions of aperiodic-unichain, non-degeneracy, and local s"},"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":"2405.17882","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T07:08:29Z","cross_cats_sorted":["math.OC","math.PR"],"title_canon_sha256":"3ec11a8b03732970913f2d63f5e48c1525bb2404669e23ab6fd3eac1b3546b7d","abstract_canon_sha256":"1c1e161aac4ae739ef8a9d57d21dba6d3ad56254d2b06ccb9af486ecb50515ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:44.702133Z","signature_b64":"SCJwTgTjF/aAFsS4xHQGVlK+FkEDLVgzcuOvuqMkcmuXHexeB3b7wAdGP2XRB0mSodoeU6sIM7bYZ+c7eta3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a75f7fac8c0e78908c410c33dac358129425e3007bdf9fd9a5982ffc0ca51639","last_reissued_at":"2026-07-05T09:21:44.701639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:44.701639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","math.PR"],"primary_cat":"cs.LG","authors_text":"Qiaomin Xie, Weina Wang, Yige Hong, Yudong Chen","submitted_at":"2024-05-28T07:08:29Z","abstract_excerpt":"We consider the infinite-horizon average-reward restless bandit problem. We propose a novel \\emph{two-set policy} that maintains two dynamic subsets of arms: one subset of arms has a nearly optimal state distribution and takes actions according to an Optimal Local Control routine; the other subset of arms is driven towards the optimal state distribution and gradually merged into the first subset. We show that our two-set policy is asymptotically optimal with an $O(\\exp(-C N))$ optimality gap for an $N$-armed problem, under the mild assumptions of aperiodic-unichain, non-degeneracy, and local s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17882","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/2405.17882/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":"2405.17882","created_at":"2026-07-05T09:21:44.701700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17882v2","created_at":"2026-07-05T09:21:44.701700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17882","created_at":"2026-07-05T09:21:44.701700+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5PX7LEMBZ4J","created_at":"2026-07-05T09:21:44.701700+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5PX7LEMBZ4JBDCB","created_at":"2026-07-05T09:21:44.701700+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5PX7LEM","created_at":"2026-07-05T09:21:44.701700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15683","citing_title":"Weakly-Coupled Multi-Action Restless Bandits -- Exponential Convergence in Probability","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK","json":"https://pith.science/pith/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK.json","graph_json":"https://pith.science/api/pith-number/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK/graph.json","events_json":"https://pith.science/api/pith-number/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK/events.json","paper":"https://pith.science/paper/U5PX7LEM"},"agent_actions":{"view_html":"https://pith.science/pith/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK","download_json":"https://pith.science/pith/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK.json","view_paper":"https://pith.science/paper/U5PX7LEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17882&json=true","fetch_graph":"https://pith.science/api/pith-number/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK/graph.json","fetch_events":"https://pith.science/api/pith-number/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK/action/storage_attestation","attest_author":"https://pith.science/pith/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK/action/author_attestation","sign_citation":"https://pith.science/pith/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK/action/citation_signature","submit_replication":"https://pith.science/pith/U5PX7LEMBZ4JBDCBBQZ5VQ2YCK/action/replication_record"}},"created_at":"2026-07-05T09:21:44.701700+00:00","updated_at":"2026-07-05T09:21:44.701700+00:00"}