{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MRQ3VIWNX7EB6LBLEW3BWBV76D","short_pith_number":"pith:MRQ3VIWN","schema_version":"1.0","canonical_sha256":"6461baa2cdbfc81f2c2b25b61b06bff0e86bc00bf03cb8706165b10349ef82c9","source":{"kind":"arxiv","id":"1907.03053","version":1},"attestation_state":"computed","paper":{"title":"A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ji Liu, Kaiqing Zhang, Romeil Sandhu, Tamer Ba\\c{s}ar, Yixuan Lin, Zhaoran Wang, Zhuoran Yang","submitted_at":"2019-07-06T00:20:50Z","abstract_excerpt":"This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors. A randomized communication-efficient multi-agent actor-critic algorithm is proposed for possibly unidirectional communication relationships depicted by a directed graph. It is shown that the algorithm can solve the problem for strongly connected graphs by allowing each agent to transmit only two scalar-valued variables at one time."},"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":"1907.03053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T00:20:50Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"9211e11584d521f8294ea5fb8fa1be3a72d4253e7cbf534f580ff16de57db6d3","abstract_canon_sha256":"d264d95b4060ae9dcffaf598cee0f1d9978fb8d42b74a28f0bd1973dc9998444"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:19.048874Z","signature_b64":"WgM53iaRsZjqVyrQz7xreFyDzInAsYWaCgvA6XMaMPTpqUeOCmeCef2Rdb7pyszmGP8LnhDrwLyLnZZ08/0KAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6461baa2cdbfc81f2c2b25b61b06bff0e86bc00bf03cb8706165b10349ef82c9","last_reissued_at":"2026-05-17T23:41:19.048336Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:19.048336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ji Liu, Kaiqing Zhang, Romeil Sandhu, Tamer Ba\\c{s}ar, Yixuan Lin, Zhaoran Wang, Zhuoran Yang","submitted_at":"2019-07-06T00:20:50Z","abstract_excerpt":"This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors. A randomized communication-efficient multi-agent actor-critic algorithm is proposed for possibly unidirectional communication relationships depicted by a directed graph. It is shown that the algorithm can solve the problem for strongly connected graphs by allowing each agent to transmit only two scalar-valued variables at one time."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03053","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":""},"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":"1907.03053","created_at":"2026-05-17T23:41:19.048430+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.03053v1","created_at":"2026-05-17T23:41:19.048430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03053","created_at":"2026-05-17T23:41:19.048430+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRQ3VIWNX7EB","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRQ3VIWNX7EB6LBL","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRQ3VIWN","created_at":"2026-05-18T12:33:21.387695+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/MRQ3VIWNX7EB6LBLEW3BWBV76D","json":"https://pith.science/pith/MRQ3VIWNX7EB6LBLEW3BWBV76D.json","graph_json":"https://pith.science/api/pith-number/MRQ3VIWNX7EB6LBLEW3BWBV76D/graph.json","events_json":"https://pith.science/api/pith-number/MRQ3VIWNX7EB6LBLEW3BWBV76D/events.json","paper":"https://pith.science/paper/MRQ3VIWN"},"agent_actions":{"view_html":"https://pith.science/pith/MRQ3VIWNX7EB6LBLEW3BWBV76D","download_json":"https://pith.science/pith/MRQ3VIWNX7EB6LBLEW3BWBV76D.json","view_paper":"https://pith.science/paper/MRQ3VIWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.03053&json=true","fetch_graph":"https://pith.science/api/pith-number/MRQ3VIWNX7EB6LBLEW3BWBV76D/graph.json","fetch_events":"https://pith.science/api/pith-number/MRQ3VIWNX7EB6LBLEW3BWBV76D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRQ3VIWNX7EB6LBLEW3BWBV76D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRQ3VIWNX7EB6LBLEW3BWBV76D/action/storage_attestation","attest_author":"https://pith.science/pith/MRQ3VIWNX7EB6LBLEW3BWBV76D/action/author_attestation","sign_citation":"https://pith.science/pith/MRQ3VIWNX7EB6LBLEW3BWBV76D/action/citation_signature","submit_replication":"https://pith.science/pith/MRQ3VIWNX7EB6LBLEW3BWBV76D/action/replication_record"}},"created_at":"2026-05-17T23:41:19.048430+00:00","updated_at":"2026-05-17T23:41:19.048430+00:00"}