{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:44NKNQY35TW3XFWWWNMCXASNVS","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":"6f8147acc0394d47d6452b380f747d78c96004bc484fd38e741951c16f92e78f","cross_cats_sorted":["cs.AI","cs.MA","cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-09T02:33:57Z","title_canon_sha256":"eb35267b76c83de80e93017fa43680a35d996e23fcbdf6761a746970b667628f"},"schema_version":"1.0","source":{"id":"1912.03821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.03821","created_at":"2026-07-05T00:24:49Z"},{"alias_kind":"arxiv_version","alias_value":"1912.03821v1","created_at":"2026-07-05T00:24:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03821","created_at":"2026-07-05T00:24:49Z"},{"alias_kind":"pith_short_12","alias_value":"44NKNQY35TW3","created_at":"2026-07-05T00:24:49Z"},{"alias_kind":"pith_short_16","alias_value":"44NKNQY35TW3XFWW","created_at":"2026-07-05T00:24:49Z"},{"alias_kind":"pith_short_8","alias_value":"44NKNQY3","created_at":"2026-07-05T00:24:49Z"}],"graph_snapshots":[{"event_id":"sha256:becd36f78b2aad67cae35bbc96c2cd07d31059741e76ca596185cfa6cf12713a","target":"graph","created_at":"2026-07-05T00:24:49Z","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/1912.03821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning (MARL) has long been a significant and everlasting research topic in both machine learning and control. With the recent development of (single-agent) deep RL, there is a resurgence of interests in developing new MARL algorithms, especially those that are backed by theoretical analysis. In this paper, we review some recent advances a sub-area of this topic: decentralized MARL with networked agents. Specifically, multiple agents perform sequential decision-making in a common environment, without the coordination of any central controller. Instead, the agents ar","authors_text":"Kaiqing Zhang, Tamer Ba\\c{s}ar, Zhuoran Yang","cross_cats":["cs.AI","cs.MA","cs.SY","eess.SY","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-09T02:33:57Z","title":"Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03821","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":"sha256:030d52fd6f160319077b8a8ae1bea6cbc3dbe1f578489a5bc5807cb0007bb066","target":"record","created_at":"2026-07-05T00:24:49Z","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":"6f8147acc0394d47d6452b380f747d78c96004bc484fd38e741951c16f92e78f","cross_cats_sorted":["cs.AI","cs.MA","cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-09T02:33:57Z","title_canon_sha256":"eb35267b76c83de80e93017fa43680a35d996e23fcbdf6761a746970b667628f"},"schema_version":"1.0","source":{"id":"1912.03821","kind":"arxiv","version":1}},"canonical_sha256":"e71aa6c31becedbb96d6b3582b824dac85b1abcc05e74c4fdd686d901c28211c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e71aa6c31becedbb96d6b3582b824dac85b1abcc05e74c4fdd686d901c28211c","first_computed_at":"2026-07-05T00:24:49.114685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:24:49.114685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Of6o6+vVOZpxHvFwDct1T9OqmAa1uHjCfn8O5Gc10Tj/HVQ4Yv/uvP4H7leFR0wPos3hVFkL9z4Z7sWKleabDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:24:49.115042Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.03821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:030d52fd6f160319077b8a8ae1bea6cbc3dbe1f578489a5bc5807cb0007bb066","sha256:becd36f78b2aad67cae35bbc96c2cd07d31059741e76ca596185cfa6cf12713a"],"state_sha256":"ce19252974c6f5973b76d6ea7f1b4e9cd162e410cd4e0a38c6c872cea0bb641f"}