{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NTB7RKPREKGRPULLONUUUAHTNU","short_pith_number":"pith:NTB7RKPR","schema_version":"1.0","canonical_sha256":"6cc3f8a9f1228d17d16b73694a00f36d337bfa15c77d0bf04b11f70f94db73f1","source":{"kind":"arxiv","id":"2607.21876","version":1},"attestation_state":"computed","paper":{"title":"Variance-Reduced Q-Learning over Static and Time-Varying Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra, Feng Zhu, Robert W. Heath Jr, Sreejeet Maity","submitted_at":"2026-07-24T00:24:09Z","abstract_excerpt":"We investigate a decentralized reinforcement learning problem involving multiple agents that interact with the same Markov Decision Process (MDP). The agents can exchange information over a network to collectively learn the optimal state-action value function. For this setting, we introduce a novel epoch-based distributed $Q$-learning algorithm called VRDQ, where within each epoch, agents locally estimate the Bellman optimality operator and diffuse information using a consensus-based protocol. For both static and time-varying networks, we establish high-probability finite-time convergence rate"},"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":"2607.21876","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T00:24:09Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"aa6076fad5cfa373ea213f97b02ef56fb10ffddfe3766a2a89d50be6b2512c59","abstract_canon_sha256":"c510a86333f7dc7d4f528e71d528abe8e0836a5d70038eef508a205e3dd86e71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:25.874838Z","signature_b64":"3cgdOCALLqqnSNN5225+tWzWGrQdnSTZE2Efi9aBVljbwO/prR3a/bhJLbc3n4OFt8JB902xP8Hs43WQaF+QCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cc3f8a9f1228d17d16b73694a00f36d337bfa15c77d0bf04b11f70f94db73f1","last_reissued_at":"2026-07-27T00:20:25.874027Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:25.874027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance-Reduced Q-Learning over Static and Time-Varying Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra, Feng Zhu, Robert W. Heath Jr, Sreejeet Maity","submitted_at":"2026-07-24T00:24:09Z","abstract_excerpt":"We investigate a decentralized reinforcement learning problem involving multiple agents that interact with the same Markov Decision Process (MDP). The agents can exchange information over a network to collectively learn the optimal state-action value function. For this setting, we introduce a novel epoch-based distributed $Q$-learning algorithm called VRDQ, where within each epoch, agents locally estimate the Bellman optimality operator and diffuse information using a consensus-based protocol. For both static and time-varying networks, we establish high-probability finite-time convergence rate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21876","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/2607.21876/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":"2607.21876","created_at":"2026-07-27T00:20:25.874450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21876v1","created_at":"2026-07-27T00:20:25.874450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21876","created_at":"2026-07-27T00:20:25.874450+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTB7RKPREKGR","created_at":"2026-07-27T00:20:25.874450+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTB7RKPREKGRPULL","created_at":"2026-07-27T00:20:25.874450+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTB7RKPR","created_at":"2026-07-27T00:20:25.874450+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/NTB7RKPREKGRPULLONUUUAHTNU","json":"https://pith.science/pith/NTB7RKPREKGRPULLONUUUAHTNU.json","graph_json":"https://pith.science/api/pith-number/NTB7RKPREKGRPULLONUUUAHTNU/graph.json","events_json":"https://pith.science/api/pith-number/NTB7RKPREKGRPULLONUUUAHTNU/events.json","paper":"https://pith.science/paper/NTB7RKPR"},"agent_actions":{"view_html":"https://pith.science/pith/NTB7RKPREKGRPULLONUUUAHTNU","download_json":"https://pith.science/pith/NTB7RKPREKGRPULLONUUUAHTNU.json","view_paper":"https://pith.science/paper/NTB7RKPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21876&json=true","fetch_graph":"https://pith.science/api/pith-number/NTB7RKPREKGRPULLONUUUAHTNU/graph.json","fetch_events":"https://pith.science/api/pith-number/NTB7RKPREKGRPULLONUUUAHTNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTB7RKPREKGRPULLONUUUAHTNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTB7RKPREKGRPULLONUUUAHTNU/action/storage_attestation","attest_author":"https://pith.science/pith/NTB7RKPREKGRPULLONUUUAHTNU/action/author_attestation","sign_citation":"https://pith.science/pith/NTB7RKPREKGRPULLONUUUAHTNU/action/citation_signature","submit_replication":"https://pith.science/pith/NTB7RKPREKGRPULLONUUUAHTNU/action/replication_record"}},"created_at":"2026-07-27T00:20:25.874450+00:00","updated_at":"2026-07-27T00:20:25.874450+00:00"}