{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VKKK6UWZKLTTM5ESIP7GOEM7DA","short_pith_number":"pith:VKKK6UWZ","schema_version":"1.0","canonical_sha256":"aa94af52d952e736749243fe67119f180d427663d4657a540cc34859581e682e","source":{"kind":"arxiv","id":"2209.08244","version":2},"attestation_state":"computed","paper":{"title":"MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Chuang Gan, Jiechuan Jiang, Kefan Su, Siyuan Zhou, Xiangjun Wang, Zongqing Lu","submitted_at":"2022-09-17T04:54:32Z","abstract_excerpt":"Decentralized learning has shown great promise for cooperative multi-agent reinforcement learning (MARL). However, non-stationarity remains a significant challenge in fully decentralized learning. In the paper, we tackle the non-stationarity problem in the simplest and fundamental way and propose multi-agent alternate Q-learning (MA2QL), where agents take turns updating their Q-functions by Q-learning. MA2QL is a minimalist approach to fully decentralized cooperative MARL but is theoretically grounded. We prove that when each agent guarantees $\\varepsilon$-convergence at each turn, their joint"},"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":"2209.08244","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-17T04:54:32Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"e57d753ec474e7e2a98d5ef47a9d61b185311995e27a47f3ceb22b347d0b8dc5","abstract_canon_sha256":"9e960bb7d0f908d5b7b4990d8d44d70818ecbca3966e7cf7f4b3e4103ec74c89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:20.072118Z","signature_b64":"XjTLMyknjk+mgToCMhWF3wRcfumDVYPpxuMX4XiPhih/e7j7p4vKqywVzMQ4De1ZfvNmAqcbWl/xdjmG58zZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa94af52d952e736749243fe67119f180d427663d4657a540cc34859581e682e","last_reissued_at":"2026-07-05T05:39:20.071577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:20.071577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Chuang Gan, Jiechuan Jiang, Kefan Su, Siyuan Zhou, Xiangjun Wang, Zongqing Lu","submitted_at":"2022-09-17T04:54:32Z","abstract_excerpt":"Decentralized learning has shown great promise for cooperative multi-agent reinforcement learning (MARL). However, non-stationarity remains a significant challenge in fully decentralized learning. In the paper, we tackle the non-stationarity problem in the simplest and fundamental way and propose multi-agent alternate Q-learning (MA2QL), where agents take turns updating their Q-functions by Q-learning. MA2QL is a minimalist approach to fully decentralized cooperative MARL but is theoretically grounded. We prove that when each agent guarantees $\\varepsilon$-convergence at each turn, their joint"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08244","kind":"arxiv","version":2},"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/2209.08244/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":"2209.08244","created_at":"2026-07-05T05:39:20.071647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08244v2","created_at":"2026-07-05T05:39:20.071647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08244","created_at":"2026-07-05T05:39:20.071647+00:00"},{"alias_kind":"pith_short_12","alias_value":"VKKK6UWZKLTT","created_at":"2026-07-05T05:39:20.071647+00:00"},{"alias_kind":"pith_short_16","alias_value":"VKKK6UWZKLTTM5ES","created_at":"2026-07-05T05:39:20.071647+00:00"},{"alias_kind":"pith_short_8","alias_value":"VKKK6UWZ","created_at":"2026-07-05T05:39:20.071647+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/VKKK6UWZKLTTM5ESIP7GOEM7DA","json":"https://pith.science/pith/VKKK6UWZKLTTM5ESIP7GOEM7DA.json","graph_json":"https://pith.science/api/pith-number/VKKK6UWZKLTTM5ESIP7GOEM7DA/graph.json","events_json":"https://pith.science/api/pith-number/VKKK6UWZKLTTM5ESIP7GOEM7DA/events.json","paper":"https://pith.science/paper/VKKK6UWZ"},"agent_actions":{"view_html":"https://pith.science/pith/VKKK6UWZKLTTM5ESIP7GOEM7DA","download_json":"https://pith.science/pith/VKKK6UWZKLTTM5ESIP7GOEM7DA.json","view_paper":"https://pith.science/paper/VKKK6UWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08244&json=true","fetch_graph":"https://pith.science/api/pith-number/VKKK6UWZKLTTM5ESIP7GOEM7DA/graph.json","fetch_events":"https://pith.science/api/pith-number/VKKK6UWZKLTTM5ESIP7GOEM7DA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VKKK6UWZKLTTM5ESIP7GOEM7DA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VKKK6UWZKLTTM5ESIP7GOEM7DA/action/storage_attestation","attest_author":"https://pith.science/pith/VKKK6UWZKLTTM5ESIP7GOEM7DA/action/author_attestation","sign_citation":"https://pith.science/pith/VKKK6UWZKLTTM5ESIP7GOEM7DA/action/citation_signature","submit_replication":"https://pith.science/pith/VKKK6UWZKLTTM5ESIP7GOEM7DA/action/replication_record"}},"created_at":"2026-07-05T05:39:20.071647+00:00","updated_at":"2026-07-05T05:39:20.071647+00:00"}