{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VVNJZEDORDQTGOIITR5746S4YA","short_pith_number":"pith:VVNJZEDO","schema_version":"1.0","canonical_sha256":"ad5a9c906e88e13339089c7bfe7a5cc030f8c4569a41a87153639d8ef3fcacd5","source":{"kind":"arxiv","id":"2206.10073","version":1},"attestation_state":"computed","paper":{"title":"Finding Optimal Policy for Queueing Models: New Parameterization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Katya Scheinberg, Lam M. Nguyen, Trang H. Tran","submitted_at":"2022-06-21T01:51:33Z","abstract_excerpt":"Queueing systems appear in many important real-life applications including communication networks, transportation and manufacturing systems. Reinforcement learning (RL) framework is a suitable model for the queueing control problem where the underlying dynamics are usually unknown and the agent receives little information from the environment to navigate. In this work, we investigate the optimization aspects of the queueing model as a RL environment and provide insight to learn the optimal policy efficiently. We propose a new parameterization of the policy by using the intrinsic properties of "},"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":"2206.10073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-06-21T01:51:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cccb6d2230837b00b5b8fc55a271b4c1cd491500044a49cb972147ecbc9acb86","abstract_canon_sha256":"c0123b9ea4d1bf06be2f5dfb83171d6c1f42fe688b86fc6cc6888958baf8f5d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:43.248350Z","signature_b64":"Eg20RD8HqjUP4Gj0OutwrwqdCv1qD/WwUOTtvAmAqNiq4228E5GHp3C42TZxWyOImDMrchK5gL9n6mWyRE2nDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad5a9c906e88e13339089c7bfe7a5cc030f8c4569a41a87153639d8ef3fcacd5","last_reissued_at":"2026-07-05T04:33:43.247934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:43.247934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding Optimal Policy for Queueing Models: New Parameterization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Katya Scheinberg, Lam M. Nguyen, Trang H. Tran","submitted_at":"2022-06-21T01:51:33Z","abstract_excerpt":"Queueing systems appear in many important real-life applications including communication networks, transportation and manufacturing systems. Reinforcement learning (RL) framework is a suitable model for the queueing control problem where the underlying dynamics are usually unknown and the agent receives little information from the environment to navigate. In this work, we investigate the optimization aspects of the queueing model as a RL environment and provide insight to learn the optimal policy efficiently. We propose a new parameterization of the policy by using the intrinsic properties of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10073","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/2206.10073/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":"2206.10073","created_at":"2026-07-05T04:33:43.247993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.10073v1","created_at":"2026-07-05T04:33:43.247993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10073","created_at":"2026-07-05T04:33:43.247993+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVNJZEDORDQT","created_at":"2026-07-05T04:33:43.247993+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVNJZEDORDQTGOII","created_at":"2026-07-05T04:33:43.247993+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVNJZEDO","created_at":"2026-07-05T04:33:43.247993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.15720","citing_title":"SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VVNJZEDORDQTGOIITR5746S4YA","json":"https://pith.science/pith/VVNJZEDORDQTGOIITR5746S4YA.json","graph_json":"https://pith.science/api/pith-number/VVNJZEDORDQTGOIITR5746S4YA/graph.json","events_json":"https://pith.science/api/pith-number/VVNJZEDORDQTGOIITR5746S4YA/events.json","paper":"https://pith.science/paper/VVNJZEDO"},"agent_actions":{"view_html":"https://pith.science/pith/VVNJZEDORDQTGOIITR5746S4YA","download_json":"https://pith.science/pith/VVNJZEDORDQTGOIITR5746S4YA.json","view_paper":"https://pith.science/paper/VVNJZEDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.10073&json=true","fetch_graph":"https://pith.science/api/pith-number/VVNJZEDORDQTGOIITR5746S4YA/graph.json","fetch_events":"https://pith.science/api/pith-number/VVNJZEDORDQTGOIITR5746S4YA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVNJZEDORDQTGOIITR5746S4YA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVNJZEDORDQTGOIITR5746S4YA/action/storage_attestation","attest_author":"https://pith.science/pith/VVNJZEDORDQTGOIITR5746S4YA/action/author_attestation","sign_citation":"https://pith.science/pith/VVNJZEDORDQTGOIITR5746S4YA/action/citation_signature","submit_replication":"https://pith.science/pith/VVNJZEDORDQTGOIITR5746S4YA/action/replication_record"}},"created_at":"2026-07-05T04:33:43.247993+00:00","updated_at":"2026-07-05T04:33:43.247993+00:00"}