{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NTB7RKPREKGRPULLONUUUAHTNU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c510a86333f7dc7d4f528e71d528abe8e0836a5d70038eef508a205e3dd86e71","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T00:24:09Z","title_canon_sha256":"aa6076fad5cfa373ea213f97b02ef56fb10ffddfe3766a2a89d50be6b2512c59"},"schema_version":"1.0","source":{"id":"2607.21876","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21876","created_at":"2026-07-27T00:20:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21876v1","created_at":"2026-07-27T00:20:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21876","created_at":"2026-07-27T00:20:25Z"},{"alias_kind":"pith_short_12","alias_value":"NTB7RKPREKGR","created_at":"2026-07-27T00:20:25Z"},{"alias_kind":"pith_short_16","alias_value":"NTB7RKPREKGRPULL","created_at":"2026-07-27T00:20:25Z"},{"alias_kind":"pith_short_8","alias_value":"NTB7RKPR","created_at":"2026-07-27T00:20:25Z"}],"graph_snapshots":[{"event_id":"sha256:1625d76d9dbfc276eb765fa6b8d02a37939044e27b03da8ec19fa6dc53cbe289","target":"graph","created_at":"2026-07-27T00:20:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.21876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aritra Mitra, Feng Zhu, Robert W. Heath Jr, Sreejeet Maity","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T00:24:09Z","title":"Variance-Reduced Q-Learning over Static and Time-Varying Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21876","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:916ff1d76fbe0e223ffc1b5379f509cdeebd6fb476350c5b9bfb9e17aed2dbce","target":"record","created_at":"2026-07-27T00:20:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c510a86333f7dc7d4f528e71d528abe8e0836a5d70038eef508a205e3dd86e71","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T00:24:09Z","title_canon_sha256":"aa6076fad5cfa373ea213f97b02ef56fb10ffddfe3766a2a89d50be6b2512c59"},"schema_version":"1.0","source":{"id":"2607.21876","kind":"arxiv","version":1}},"canonical_sha256":"6cc3f8a9f1228d17d16b73694a00f36d337bfa15c77d0bf04b11f70f94db73f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cc3f8a9f1228d17d16b73694a00f36d337bfa15c77d0bf04b11f70f94db73f1","first_computed_at":"2026-07-27T00:20:25.874027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T00:20:25.874027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3cgdOCALLqqnSNN5225+tWzWGrQdnSTZE2Efi9aBVljbwO/prR3a/bhJLbc3n4OFt8JB902xP8Hs43WQaF+QCQ==","signature_status":"signed_v1","signed_at":"2026-07-27T00:20:25.874838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21876","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:916ff1d76fbe0e223ffc1b5379f509cdeebd6fb476350c5b9bfb9e17aed2dbce","sha256:1625d76d9dbfc276eb765fa6b8d02a37939044e27b03da8ec19fa6dc53cbe289"],"state_sha256":"088eb60f7b7375b8364ca02133700088daddfd59bf51669e798a5281a92c08d9"}