{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LONXKJEQB2GHXRM3MS37LX5W64","short_pith_number":"pith:LONXKJEQ","schema_version":"1.0","canonical_sha256":"5b9b7524900e8c7bc59b64b7f5dfb6f73c533fbbaae59e85a2648009581a3e7b","source":{"kind":"arxiv","id":"2406.04766","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning and Regret Bounds for Admission Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ana Bu\\v{s}i\\'c, Jiamin Zhu, Lucas Weber","submitted_at":"2024-06-07T09:09:14Z","abstract_excerpt":"The expected regret of any reinforcement learning algorithm is lower bounded by $\\Omega\\left(\\sqrt{DXAT}\\right)$ for undiscounted returns, where $D$ is the diameter of the Markov decision process, $X$ the size of the state space, $A$ the size of the action space and $T$ the number of time steps. However, this lower bound is general. A smaller regret can be obtained by taking into account some specific knowledge of the problem structure. In this article, we consider an admission control problem to an $M/M/c/S$ queue with $m$ job classes and class-dependent rewards and holding costs. Queuing sys"},"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":"2406.04766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T09:09:14Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"e59ff73da5557ccd84b1d4a55e946861387dde33d588d0b1341cbc9669507f81","abstract_canon_sha256":"56588b191cd66cdc9708dcd5c1284ceb4df64dfd08b6615bdb29ca7545c3f6a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:49.158945Z","signature_b64":"1c9TlVpSAyoC9uTrSknAXoeYq82bOxNKxYbgOpYMxWhilccpbArPXaBWtDdDzNPTO3XlVwB+Mx2mPg3BAMPYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b9b7524900e8c7bc59b64b7f5dfb6f73c533fbbaae59e85a2648009581a3e7b","last_reissued_at":"2026-07-05T08:28:49.158556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:49.158556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning and Regret Bounds for Admission Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ana Bu\\v{s}i\\'c, Jiamin Zhu, Lucas Weber","submitted_at":"2024-06-07T09:09:14Z","abstract_excerpt":"The expected regret of any reinforcement learning algorithm is lower bounded by $\\Omega\\left(\\sqrt{DXAT}\\right)$ for undiscounted returns, where $D$ is the diameter of the Markov decision process, $X$ the size of the state space, $A$ the size of the action space and $T$ the number of time steps. However, this lower bound is general. A smaller regret can be obtained by taking into account some specific knowledge of the problem structure. In this article, we consider an admission control problem to an $M/M/c/S$ queue with $m$ job classes and class-dependent rewards and holding costs. Queuing sys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04766","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.04766/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":"2406.04766","created_at":"2026-07-05T08:28:49.158617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04766v1","created_at":"2026-07-05T08:28:49.158617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04766","created_at":"2026-07-05T08:28:49.158617+00:00"},{"alias_kind":"pith_short_12","alias_value":"LONXKJEQB2GH","created_at":"2026-07-05T08:28:49.158617+00:00"},{"alias_kind":"pith_short_16","alias_value":"LONXKJEQB2GHXRM3","created_at":"2026-07-05T08:28:49.158617+00:00"},{"alias_kind":"pith_short_8","alias_value":"LONXKJEQ","created_at":"2026-07-05T08:28:49.158617+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/LONXKJEQB2GHXRM3MS37LX5W64","json":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64.json","graph_json":"https://pith.science/api/pith-number/LONXKJEQB2GHXRM3MS37LX5W64/graph.json","events_json":"https://pith.science/api/pith-number/LONXKJEQB2GHXRM3MS37LX5W64/events.json","paper":"https://pith.science/paper/LONXKJEQ"},"agent_actions":{"view_html":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64","download_json":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64.json","view_paper":"https://pith.science/paper/LONXKJEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04766&json=true","fetch_graph":"https://pith.science/api/pith-number/LONXKJEQB2GHXRM3MS37LX5W64/graph.json","fetch_events":"https://pith.science/api/pith-number/LONXKJEQB2GHXRM3MS37LX5W64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64/action/storage_attestation","attest_author":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64/action/author_attestation","sign_citation":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64/action/citation_signature","submit_replication":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64/action/replication_record"}},"created_at":"2026-07-05T08:28:49.158617+00:00","updated_at":"2026-07-05T08:28:49.158617+00:00"}