{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UFI5CNPLAIEMQZ73Y6SBWGLPBZ","short_pith_number":"pith:UFI5CNPL","schema_version":"1.0","canonical_sha256":"a151d135eb0208c867fbc7a41b196f0e585b7afbef931f5644f19a631c7d2065","source":{"kind":"arxiv","id":"1812.02783","version":8},"attestation_state":"computed","paper":{"title":"Finite-Sample Analysis For Decentralized Batch Multi-Agent Reinforcement Learning With Networked Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Liu, Kaiqing Zhang, Tamer Ba\\c{s}ar, Tong Zhang, Zhuoran Yang","submitted_at":"2018-12-06T20:09:40Z","abstract_excerpt":"Despite the increasing interest in multi-agent reinforcement learning (MARL) in multiple communities, understanding its theoretical foundation has long been recognized as a challenging problem. In this work, we address this problem by providing a finite-sample analysis for decentralized batch MARL with networked agents. Specifically, we consider two decentralized MARL settings, where teams of agents are connected by time-varying communication networks, and either collaborate or compete in a zero-sum game setting, without any central controller. These settings cover many conventional MARL setti"},"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":"1812.02783","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T20:09:40Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"f9ab184d98a79fea1875795efefa0fb9d47a44f35f3f84ec3641d7cf7bde1bb4","abstract_canon_sha256":"f7f087b027f5e0953e8cdb3bc9ff6358149af594b1c9de7e7d1ecbf612f94e48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:08.406273Z","signature_b64":"P8/EvdiPqEoegKRyG78jamtHe0tH6OgcPp21VrXZWpLFcqCwCxwvjryKlG7X6y/p25NZNrxl7/NMBGRADm5XDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a151d135eb0208c867fbc7a41b196f0e585b7afbef931f5644f19a631c7d2065","last_reissued_at":"2026-07-05T01:59:08.405827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:08.405827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-Sample Analysis For Decentralized Batch Multi-Agent Reinforcement Learning With Networked Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Liu, Kaiqing Zhang, Tamer Ba\\c{s}ar, Tong Zhang, Zhuoran Yang","submitted_at":"2018-12-06T20:09:40Z","abstract_excerpt":"Despite the increasing interest in multi-agent reinforcement learning (MARL) in multiple communities, understanding its theoretical foundation has long been recognized as a challenging problem. In this work, we address this problem by providing a finite-sample analysis for decentralized batch MARL with networked agents. Specifically, we consider two decentralized MARL settings, where teams of agents are connected by time-varying communication networks, and either collaborate or compete in a zero-sum game setting, without any central controller. These settings cover many conventional MARL setti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02783","kind":"arxiv","version":8},"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/1812.02783/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":"1812.02783","created_at":"2026-07-05T01:59:08.405901+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02783v8","created_at":"2026-07-05T01:59:08.405901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02783","created_at":"2026-07-05T01:59:08.405901+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFI5CNPLAIEM","created_at":"2026-07-05T01:59:08.405901+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFI5CNPLAIEMQZ73","created_at":"2026-07-05T01:59:08.405901+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFI5CNPL","created_at":"2026-07-05T01:59:08.405901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.03053","citing_title":"A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFI5CNPLAIEMQZ73Y6SBWGLPBZ","json":"https://pith.science/pith/UFI5CNPLAIEMQZ73Y6SBWGLPBZ.json","graph_json":"https://pith.science/api/pith-number/UFI5CNPLAIEMQZ73Y6SBWGLPBZ/graph.json","events_json":"https://pith.science/api/pith-number/UFI5CNPLAIEMQZ73Y6SBWGLPBZ/events.json","paper":"https://pith.science/paper/UFI5CNPL"},"agent_actions":{"view_html":"https://pith.science/pith/UFI5CNPLAIEMQZ73Y6SBWGLPBZ","download_json":"https://pith.science/pith/UFI5CNPLAIEMQZ73Y6SBWGLPBZ.json","view_paper":"https://pith.science/paper/UFI5CNPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02783&json=true","fetch_graph":"https://pith.science/api/pith-number/UFI5CNPLAIEMQZ73Y6SBWGLPBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UFI5CNPLAIEMQZ73Y6SBWGLPBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFI5CNPLAIEMQZ73Y6SBWGLPBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFI5CNPLAIEMQZ73Y6SBWGLPBZ/action/storage_attestation","attest_author":"https://pith.science/pith/UFI5CNPLAIEMQZ73Y6SBWGLPBZ/action/author_attestation","sign_citation":"https://pith.science/pith/UFI5CNPLAIEMQZ73Y6SBWGLPBZ/action/citation_signature","submit_replication":"https://pith.science/pith/UFI5CNPLAIEMQZ73Y6SBWGLPBZ/action/replication_record"}},"created_at":"2026-07-05T01:59:08.405901+00:00","updated_at":"2026-07-05T01:59:08.405901+00:00"}