{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:ZR6LQ563OVK4DILQ5Q2HGOJUWD","short_pith_number":"pith:ZR6LQ563","schema_version":"1.0","canonical_sha256":"cc7cb877db7555c1a170ec34733934b0fd5a5d0aaae0fe06cc6cf4bbef48ab5c","source":{"kind":"arxiv","id":"1109.1533","version":1},"attestation_state":"computed","paper":{"title":"The Non-Bayesian Restless Multi-Armed Bandit: A Case of Near-Logarithmic Strict Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NI","cs.SY","math.PR"],"primary_cat":"math.OC","authors_text":"Bhaskar Krishnamachari, Qing Zhao, Wenhan Dai, Yi Gai","submitted_at":"2011-09-07T18:33:59Z","abstract_excerpt":"In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \\geq 1$ arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to be PSPACE-hard in general. We consider in this work the even harder non-Bayesian RMAB, in which the parameters of the Markov chain are assumed to be unknown \\emph{a priori}. We develop an original approach to this problem that is applicable when"},"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":"1109.1533","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-09-07T18:33:59Z","cross_cats_sorted":["cs.LG","cs.NI","cs.SY","math.PR"],"title_canon_sha256":"24f6199c68029bfcc4275ea0dcea356cbed4f7a4dee6cb60d790b8b341c30e21","abstract_canon_sha256":"9d898173976ce5d5f0497a76949556ecb78008833e935648d54f10d14e23da7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:05:47.067378Z","signature_b64":"su6X1IvRg6djNhlISz+Z4pNcHjDxh+gd1yE9pH788lDx30J7iR6/jTpbEh2hRQ/PkZ1C+gQDEgILWBn7S9uUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc7cb877db7555c1a170ec34733934b0fd5a5d0aaae0fe06cc6cf4bbef48ab5c","last_reissued_at":"2026-05-18T04:05:47.066929Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:05:47.066929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Non-Bayesian Restless Multi-Armed Bandit: A Case of Near-Logarithmic Strict Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NI","cs.SY","math.PR"],"primary_cat":"math.OC","authors_text":"Bhaskar Krishnamachari, Qing Zhao, Wenhan Dai, Yi Gai","submitted_at":"2011-09-07T18:33:59Z","abstract_excerpt":"In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \\geq 1$ arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to be PSPACE-hard in general. We consider in this work the even harder non-Bayesian RMAB, in which the parameters of the Markov chain are assumed to be unknown \\emph{a priori}. We develop an original approach to this problem that is applicable when"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1109.1533","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1109.1533","created_at":"2026-05-18T04:05:47.066995+00:00"},{"alias_kind":"arxiv_version","alias_value":"1109.1533v1","created_at":"2026-05-18T04:05:47.066995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1109.1533","created_at":"2026-05-18T04:05:47.066995+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZR6LQ563OVK4","created_at":"2026-05-18T12:26:50.516681+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZR6LQ563OVK4DILQ","created_at":"2026-05-18T12:26:50.516681+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZR6LQ563","created_at":"2026-05-18T12:26:50.516681+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/ZR6LQ563OVK4DILQ5Q2HGOJUWD","json":"https://pith.science/pith/ZR6LQ563OVK4DILQ5Q2HGOJUWD.json","graph_json":"https://pith.science/api/pith-number/ZR6LQ563OVK4DILQ5Q2HGOJUWD/graph.json","events_json":"https://pith.science/api/pith-number/ZR6LQ563OVK4DILQ5Q2HGOJUWD/events.json","paper":"https://pith.science/paper/ZR6LQ563"},"agent_actions":{"view_html":"https://pith.science/pith/ZR6LQ563OVK4DILQ5Q2HGOJUWD","download_json":"https://pith.science/pith/ZR6LQ563OVK4DILQ5Q2HGOJUWD.json","view_paper":"https://pith.science/paper/ZR6LQ563","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1109.1533&json=true","fetch_graph":"https://pith.science/api/pith-number/ZR6LQ563OVK4DILQ5Q2HGOJUWD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZR6LQ563OVK4DILQ5Q2HGOJUWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZR6LQ563OVK4DILQ5Q2HGOJUWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZR6LQ563OVK4DILQ5Q2HGOJUWD/action/storage_attestation","attest_author":"https://pith.science/pith/ZR6LQ563OVK4DILQ5Q2HGOJUWD/action/author_attestation","sign_citation":"https://pith.science/pith/ZR6LQ563OVK4DILQ5Q2HGOJUWD/action/citation_signature","submit_replication":"https://pith.science/pith/ZR6LQ563OVK4DILQ5Q2HGOJUWD/action/replication_record"}},"created_at":"2026-05-18T04:05:47.066995+00:00","updated_at":"2026-05-18T04:05:47.066995+00:00"}