{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:T4QMQ7DYWKHXZ72DZR7QLWJ7TY","short_pith_number":"pith:T4QMQ7DY","schema_version":"1.0","canonical_sha256":"9f20c87c78b28f7cff43cc7f05d93f9e269e2a40c617b2ef56e7d7eaba2f9e07","source":{"kind":"arxiv","id":"1906.04594","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning with Discrete Normalized Advantage Functions for Resource Management in Network Slicing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Qi, Honggang Zhang, Rongpeng Li, Yuxiu Hua, Zhifeng Zhao","submitted_at":"2019-06-10T05:28:44Z","abstract_excerpt":"Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep $\\mathcal{Q}$-learning, DQL) is assumed to be an appropriate algorithm to solve the demand-aware inter-slice resource management issue in network slicing by regarding the varying demands and the allocated bandwidth as the environment state and the action, respectively. However, allocating bandwidth in a finer resolution usually implies larger action space, and unfortunately DQL fails to quickly converge in this case. In this paper, we introduce di"},"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":"1906.04594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T05:28:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7b7cf2ff6b97d70f8bdc757e9600a54c76591bc26fc5675365152e537fe43ed8","abstract_canon_sha256":"d33809402900e61a5b7e49a4fb8143f5f3e7d01e292636e1b1e831466004e49f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:38.812087Z","signature_b64":"OXOXxp9KJCH6bT3/9ACv0TJW9CKCtG54exMAF9oRTLIMHeIj6ZOxQn5mS7CzFvctUmuMEtZB5AecPoGMoJuvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f20c87c78b28f7cff43cc7f05d93f9e269e2a40c617b2ef56e7d7eaba2f9e07","last_reissued_at":"2026-05-17T23:43:38.811455Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:38.811455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning with Discrete Normalized Advantage Functions for Resource Management in Network Slicing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Qi, Honggang Zhang, Rongpeng Li, Yuxiu Hua, Zhifeng Zhao","submitted_at":"2019-06-10T05:28:44Z","abstract_excerpt":"Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep $\\mathcal{Q}$-learning, DQL) is assumed to be an appropriate algorithm to solve the demand-aware inter-slice resource management issue in network slicing by regarding the varying demands and the allocated bandwidth as the environment state and the action, respectively. However, allocating bandwidth in a finer resolution usually implies larger action space, and unfortunately DQL fails to quickly converge in this case. In this paper, we introduce di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04594","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":"1906.04594","created_at":"2026-05-17T23:43:38.811546+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04594v1","created_at":"2026-05-17T23:43:38.811546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04594","created_at":"2026-05-17T23:43:38.811546+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4QMQ7DYWKHX","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4QMQ7DYWKHXZ72D","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4QMQ7DY","created_at":"2026-05-18T12:33:27.125529+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/T4QMQ7DYWKHXZ72DZR7QLWJ7TY","json":"https://pith.science/pith/T4QMQ7DYWKHXZ72DZR7QLWJ7TY.json","graph_json":"https://pith.science/api/pith-number/T4QMQ7DYWKHXZ72DZR7QLWJ7TY/graph.json","events_json":"https://pith.science/api/pith-number/T4QMQ7DYWKHXZ72DZR7QLWJ7TY/events.json","paper":"https://pith.science/paper/T4QMQ7DY"},"agent_actions":{"view_html":"https://pith.science/pith/T4QMQ7DYWKHXZ72DZR7QLWJ7TY","download_json":"https://pith.science/pith/T4QMQ7DYWKHXZ72DZR7QLWJ7TY.json","view_paper":"https://pith.science/paper/T4QMQ7DY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04594&json=true","fetch_graph":"https://pith.science/api/pith-number/T4QMQ7DYWKHXZ72DZR7QLWJ7TY/graph.json","fetch_events":"https://pith.science/api/pith-number/T4QMQ7DYWKHXZ72DZR7QLWJ7TY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4QMQ7DYWKHXZ72DZR7QLWJ7TY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4QMQ7DYWKHXZ72DZR7QLWJ7TY/action/storage_attestation","attest_author":"https://pith.science/pith/T4QMQ7DYWKHXZ72DZR7QLWJ7TY/action/author_attestation","sign_citation":"https://pith.science/pith/T4QMQ7DYWKHXZ72DZR7QLWJ7TY/action/citation_signature","submit_replication":"https://pith.science/pith/T4QMQ7DYWKHXZ72DZR7QLWJ7TY/action/replication_record"}},"created_at":"2026-05-17T23:43:38.811546+00:00","updated_at":"2026-05-17T23:43:38.811546+00:00"}