{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:44NKNQY35TW3XFWWWNMCXASNVS","short_pith_number":"pith:44NKNQY3","schema_version":"1.0","canonical_sha256":"e71aa6c31becedbb96d6b3582b824dac85b1abcc05e74c4fdd686d901c28211c","source":{"kind":"arxiv","id":"1912.03821","version":1},"attestation_state":"computed","paper":{"title":"Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaiqing Zhang, Tamer Ba\\c{s}ar, Zhuoran Yang","submitted_at":"2019-12-09T02:33:57Z","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"},"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":"1912.03821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-09T02:33:57Z","cross_cats_sorted":["cs.AI","cs.MA","cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"eb35267b76c83de80e93017fa43680a35d996e23fcbdf6761a746970b667628f","abstract_canon_sha256":"6f8147acc0394d47d6452b380f747d78c96004bc484fd38e741951c16f92e78f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:49.115042Z","signature_b64":"Of6o6+vVOZpxHvFwDct1T9OqmAa1uHjCfn8O5Gc10Tj/HVQ4Yv/uvP4H7leFR0wPos3hVFkL9z4Z7sWKleabDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e71aa6c31becedbb96d6b3582b824dac85b1abcc05e74c4fdd686d901c28211c","last_reissued_at":"2026-07-05T00:24:49.114685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:49.114685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kaiqing Zhang, Tamer Ba\\c{s}ar, Zhuoran Yang","submitted_at":"2019-12-09T02:33:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03821","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/1912.03821/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":"1912.03821","created_at":"2026-07-05T00:24:49.114734+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.03821v1","created_at":"2026-07-05T00:24:49.114734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03821","created_at":"2026-07-05T00:24:49.114734+00:00"},{"alias_kind":"pith_short_12","alias_value":"44NKNQY35TW3","created_at":"2026-07-05T00:24:49.114734+00:00"},{"alias_kind":"pith_short_16","alias_value":"44NKNQY35TW3XFWW","created_at":"2026-07-05T00:24:49.114734+00:00"},{"alias_kind":"pith_short_8","alias_value":"44NKNQY3","created_at":"2026-07-05T00:24:49.114734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.02805","citing_title":"Fast Multi-Agent Temporal-Difference Learning via Homotopy Stochastic Primal-Dual Optimization","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/44NKNQY35TW3XFWWWNMCXASNVS","json":"https://pith.science/pith/44NKNQY35TW3XFWWWNMCXASNVS.json","graph_json":"https://pith.science/api/pith-number/44NKNQY35TW3XFWWWNMCXASNVS/graph.json","events_json":"https://pith.science/api/pith-number/44NKNQY35TW3XFWWWNMCXASNVS/events.json","paper":"https://pith.science/paper/44NKNQY3"},"agent_actions":{"view_html":"https://pith.science/pith/44NKNQY35TW3XFWWWNMCXASNVS","download_json":"https://pith.science/pith/44NKNQY35TW3XFWWWNMCXASNVS.json","view_paper":"https://pith.science/paper/44NKNQY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.03821&json=true","fetch_graph":"https://pith.science/api/pith-number/44NKNQY35TW3XFWWWNMCXASNVS/graph.json","fetch_events":"https://pith.science/api/pith-number/44NKNQY35TW3XFWWWNMCXASNVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44NKNQY35TW3XFWWWNMCXASNVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44NKNQY35TW3XFWWWNMCXASNVS/action/storage_attestation","attest_author":"https://pith.science/pith/44NKNQY35TW3XFWWWNMCXASNVS/action/author_attestation","sign_citation":"https://pith.science/pith/44NKNQY35TW3XFWWWNMCXASNVS/action/citation_signature","submit_replication":"https://pith.science/pith/44NKNQY35TW3XFWWWNMCXASNVS/action/replication_record"}},"created_at":"2026-07-05T00:24:49.114734+00:00","updated_at":"2026-07-05T00:24:49.114734+00:00"}