{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:USLGY6PSEORSBE7C66LR5JCLIN","short_pith_number":"pith:USLGY6PS","schema_version":"1.0","canonical_sha256":"a4966c79f223a32093e2f7971ea44b434e432f30cac2413a759ca1f5bfabae60","source":{"kind":"arxiv","id":"1011.4752","version":1},"attestation_state":"computed","paper":{"title":"The Non-Bayesian Restless Multi-Armed Bandit: a Case of Near-Logarithmic Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NI","math.PR"],"primary_cat":"math.OC","authors_text":"Bhaskar Krishnamachari, Qing Zhao, Wenhan Dai, Yi Gai","submitted_at":"2010-11-22T09:07:55Z","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":"1011.4752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2010-11-22T09:07:55Z","cross_cats_sorted":["cs.LG","cs.NI","math.PR"],"title_canon_sha256":"05c460213fbccf99877ac760195edbc44a4297ee59fab9b571f6c8471b7ec3ac","abstract_canon_sha256":"f7ec40f254e307ac29616369a2f940f79478d9cd6669e3f2bf73e43efedd8bd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:35:04.026998Z","signature_b64":"OeTYzE6rHu7lpO/KBhYY56it0SlrdTTjPr4Vq2zv9vo2o0vZDsGRVqpiyYzpd6gawHWVl1u+smaRoj76aM8PCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4966c79f223a32093e2f7971ea44b434e432f30cac2413a759ca1f5bfabae60","last_reissued_at":"2026-05-18T04:35:04.026581Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:35:04.026581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Non-Bayesian Restless Multi-Armed Bandit: a Case of Near-Logarithmic Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NI","math.PR"],"primary_cat":"math.OC","authors_text":"Bhaskar Krishnamachari, Qing Zhao, Wenhan Dai, Yi Gai","submitted_at":"2010-11-22T09:07:55Z","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":"1011.4752","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":"1011.4752","created_at":"2026-05-18T04:35:04.026649+00:00"},{"alias_kind":"arxiv_version","alias_value":"1011.4752v1","created_at":"2026-05-18T04:35:04.026649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1011.4752","created_at":"2026-05-18T04:35:04.026649+00:00"},{"alias_kind":"pith_short_12","alias_value":"USLGY6PSEORS","created_at":"2026-05-18T12:26:15.391820+00:00"},{"alias_kind":"pith_short_16","alias_value":"USLGY6PSEORSBE7C","created_at":"2026-05-18T12:26:15.391820+00:00"},{"alias_kind":"pith_short_8","alias_value":"USLGY6PS","created_at":"2026-05-18T12:26:15.391820+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/USLGY6PSEORSBE7C66LR5JCLIN","json":"https://pith.science/pith/USLGY6PSEORSBE7C66LR5JCLIN.json","graph_json":"https://pith.science/api/pith-number/USLGY6PSEORSBE7C66LR5JCLIN/graph.json","events_json":"https://pith.science/api/pith-number/USLGY6PSEORSBE7C66LR5JCLIN/events.json","paper":"https://pith.science/paper/USLGY6PS"},"agent_actions":{"view_html":"https://pith.science/pith/USLGY6PSEORSBE7C66LR5JCLIN","download_json":"https://pith.science/pith/USLGY6PSEORSBE7C66LR5JCLIN.json","view_paper":"https://pith.science/paper/USLGY6PS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1011.4752&json=true","fetch_graph":"https://pith.science/api/pith-number/USLGY6PSEORSBE7C66LR5JCLIN/graph.json","fetch_events":"https://pith.science/api/pith-number/USLGY6PSEORSBE7C66LR5JCLIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USLGY6PSEORSBE7C66LR5JCLIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USLGY6PSEORSBE7C66LR5JCLIN/action/storage_attestation","attest_author":"https://pith.science/pith/USLGY6PSEORSBE7C66LR5JCLIN/action/author_attestation","sign_citation":"https://pith.science/pith/USLGY6PSEORSBE7C66LR5JCLIN/action/citation_signature","submit_replication":"https://pith.science/pith/USLGY6PSEORSBE7C66LR5JCLIN/action/replication_record"}},"created_at":"2026-05-18T04:35:04.026649+00:00","updated_at":"2026-05-18T04:35:04.026649+00:00"}