{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SLSELTFJYLVNNUCWAPXRACOKZI","short_pith_number":"pith:SLSELTFJ","schema_version":"1.0","canonical_sha256":"92e445cca9c2ead6d05603ef1009caca3c612d9e6af57130bfa4beaa16ca00c9","source":{"kind":"arxiv","id":"2506.04291","version":1},"attestation_state":"computed","paper":{"title":"A Lyapunov Drift-Plus-Penalty Method Tailored for Reinforcement Learning with Queue Stability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Danny Hin-Kwok Tsang, Jiashuo Jiang, Lei Deng, Wenhan Xu","submitted_at":"2025-06-04T10:56:24Z","abstract_excerpt":"With the proliferation of Internet of Things (IoT) devices, the demand for addressing complex optimization challenges has intensified. The Lyapunov Drift-Plus-Penalty algorithm is a widely adopted approach for ensuring queue stability, and some research has preliminarily explored its integration with reinforcement learning (RL). In this paper, we investigate the adaptation of the Lyapunov Drift-Plus-Penalty algorithm for RL applications, deriving an effective method for combining Lyapunov Drift-Plus-Penalty with RL under a set of common and reasonable conditions through rigorous theoretical an"},"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":"2506.04291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T10:56:24Z","cross_cats_sorted":[],"title_canon_sha256":"572273c517445723ea6f1e4cd2470e475a1469ecca6c635d2a49d907c02317f2","abstract_canon_sha256":"fbb12f39e9edf02e5808c157e8c0a9ff403cdd7087c6a3b2c185cbb7e8378ab3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:11.832613Z","signature_b64":"OAY2xdbi+PaqHzF7SMHqFImseCNpByKKynVGNBjo6r/DsBnLfIgE0ywo81fo/KepfWekxm3KVNfklmAVF1iTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92e445cca9c2ead6d05603ef1009caca3c612d9e6af57130bfa4beaa16ca00c9","last_reissued_at":"2026-07-05T11:16:11.832134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:11.832134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Lyapunov Drift-Plus-Penalty Method Tailored for Reinforcement Learning with Queue Stability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Danny Hin-Kwok Tsang, Jiashuo Jiang, Lei Deng, Wenhan Xu","submitted_at":"2025-06-04T10:56:24Z","abstract_excerpt":"With the proliferation of Internet of Things (IoT) devices, the demand for addressing complex optimization challenges has intensified. The Lyapunov Drift-Plus-Penalty algorithm is a widely adopted approach for ensuring queue stability, and some research has preliminarily explored its integration with reinforcement learning (RL). In this paper, we investigate the adaptation of the Lyapunov Drift-Plus-Penalty algorithm for RL applications, deriving an effective method for combining Lyapunov Drift-Plus-Penalty with RL under a set of common and reasonable conditions through rigorous theoretical an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04291","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/2506.04291/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":"2506.04291","created_at":"2026-07-05T11:16:11.832187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04291v1","created_at":"2026-07-05T11:16:11.832187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04291","created_at":"2026-07-05T11:16:11.832187+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLSELTFJYLVN","created_at":"2026-07-05T11:16:11.832187+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLSELTFJYLVNNUCW","created_at":"2026-07-05T11:16:11.832187+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLSELTFJ","created_at":"2026-07-05T11:16:11.832187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08452","citing_title":"Theoretical Foundations of Continual Learning via Drift-Plus-Penalty","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SLSELTFJYLVNNUCWAPXRACOKZI","json":"https://pith.science/pith/SLSELTFJYLVNNUCWAPXRACOKZI.json","graph_json":"https://pith.science/api/pith-number/SLSELTFJYLVNNUCWAPXRACOKZI/graph.json","events_json":"https://pith.science/api/pith-number/SLSELTFJYLVNNUCWAPXRACOKZI/events.json","paper":"https://pith.science/paper/SLSELTFJ"},"agent_actions":{"view_html":"https://pith.science/pith/SLSELTFJYLVNNUCWAPXRACOKZI","download_json":"https://pith.science/pith/SLSELTFJYLVNNUCWAPXRACOKZI.json","view_paper":"https://pith.science/paper/SLSELTFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04291&json=true","fetch_graph":"https://pith.science/api/pith-number/SLSELTFJYLVNNUCWAPXRACOKZI/graph.json","fetch_events":"https://pith.science/api/pith-number/SLSELTFJYLVNNUCWAPXRACOKZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLSELTFJYLVNNUCWAPXRACOKZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLSELTFJYLVNNUCWAPXRACOKZI/action/storage_attestation","attest_author":"https://pith.science/pith/SLSELTFJYLVNNUCWAPXRACOKZI/action/author_attestation","sign_citation":"https://pith.science/pith/SLSELTFJYLVNNUCWAPXRACOKZI/action/citation_signature","submit_replication":"https://pith.science/pith/SLSELTFJYLVNNUCWAPXRACOKZI/action/replication_record"}},"created_at":"2026-07-05T11:16:11.832187+00:00","updated_at":"2026-07-05T11:16:11.832187+00:00"}