{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:ZIXNSSXTBRPUNIJDMVLTQJESV3","short_pith_number":"pith:ZIXNSSXT","schema_version":"1.0","canonical_sha256":"ca2ed94af30c5f46a1236557382492aeed7fc1907907fad829b9b6addaa5fe67","source":{"kind":"arxiv","id":"1102.3508","version":1},"attestation_state":"computed","paper":{"title":"Online Learning of Rested and Restless Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Cem Tekin, Mingyan Liu","submitted_at":"2011-02-17T07:08:37Z","abstract_excerpt":"In this paper we study the online learning problem involving rested and restless multiarmed bandits with multiple plays. The system consists of a single player/user and a set of K finite-state discrete-time Markov chains (arms) with unknown state spaces and statistics. At each time step the player can play M arms. The objective of the user is to decide for each step which M of the K arms to play over a sequence of trials so as to maximize its long term reward. The restless multiarmed bandit is particularly relevant to the application of opportunistic spectrum access (OSA), where a (secondary) "},"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":"1102.3508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-02-17T07:08:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c84a2aee6333bca787958811278356b64c921eeb4bd564f6fdc59cb064a54d92","abstract_canon_sha256":"ce2c9cb60cf8e58c8b55b8393c7d014affa70fc9560e6aa5f737201bd1928221"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:20:37.354189Z","signature_b64":"DgTY5bACevvD78Au0Z4zvl9DuwnbWpcX6HR+m0XbMT9KoWlgDsx5a/do+9gYiqc8C+nGaFV8jj3nUZqF6deACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca2ed94af30c5f46a1236557382492aeed7fc1907907fad829b9b6addaa5fe67","last_reissued_at":"2026-05-18T02:20:37.353368Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:20:37.353368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Learning of Rested and Restless Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Cem Tekin, Mingyan Liu","submitted_at":"2011-02-17T07:08:37Z","abstract_excerpt":"In this paper we study the online learning problem involving rested and restless multiarmed bandits with multiple plays. The system consists of a single player/user and a set of K finite-state discrete-time Markov chains (arms) with unknown state spaces and statistics. At each time step the player can play M arms. The objective of the user is to decide for each step which M of the K arms to play over a sequence of trials so as to maximize its long term reward. The restless multiarmed bandit is particularly relevant to the application of opportunistic spectrum access (OSA), where a (secondary) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1102.3508","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":"1102.3508","created_at":"2026-05-18T02:20:37.353523+00:00"},{"alias_kind":"arxiv_version","alias_value":"1102.3508v1","created_at":"2026-05-18T02:20:37.353523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1102.3508","created_at":"2026-05-18T02:20:37.353523+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIXNSSXTBRPU","created_at":"2026-05-18T12:26:47.523578+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIXNSSXTBRPUNIJD","created_at":"2026-05-18T12:26:47.523578+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIXNSSXT","created_at":"2026-05-18T12:26:47.523578+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/ZIXNSSXTBRPUNIJDMVLTQJESV3","json":"https://pith.science/pith/ZIXNSSXTBRPUNIJDMVLTQJESV3.json","graph_json":"https://pith.science/api/pith-number/ZIXNSSXTBRPUNIJDMVLTQJESV3/graph.json","events_json":"https://pith.science/api/pith-number/ZIXNSSXTBRPUNIJDMVLTQJESV3/events.json","paper":"https://pith.science/paper/ZIXNSSXT"},"agent_actions":{"view_html":"https://pith.science/pith/ZIXNSSXTBRPUNIJDMVLTQJESV3","download_json":"https://pith.science/pith/ZIXNSSXTBRPUNIJDMVLTQJESV3.json","view_paper":"https://pith.science/paper/ZIXNSSXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1102.3508&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIXNSSXTBRPUNIJDMVLTQJESV3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIXNSSXTBRPUNIJDMVLTQJESV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIXNSSXTBRPUNIJDMVLTQJESV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIXNSSXTBRPUNIJDMVLTQJESV3/action/storage_attestation","attest_author":"https://pith.science/pith/ZIXNSSXTBRPUNIJDMVLTQJESV3/action/author_attestation","sign_citation":"https://pith.science/pith/ZIXNSSXTBRPUNIJDMVLTQJESV3/action/citation_signature","submit_replication":"https://pith.science/pith/ZIXNSSXTBRPUNIJDMVLTQJESV3/action/replication_record"}},"created_at":"2026-05-18T02:20:37.353523+00:00","updated_at":"2026-05-18T02:20:37.353523+00:00"}