{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T2ZJGHSGCESOXRTF3LBFESL6F2","short_pith_number":"pith:T2ZJGHSG","schema_version":"1.0","canonical_sha256":"9eb2931e461124ebc665dac252497e2eaf7f3436518c8ed8a4a0a1093350588a","source":{"kind":"arxiv","id":"2307.15530","version":1},"attestation_state":"computed","paper":{"title":"Learning to Collaborate by Grouping: a Consensus-oriented Strategy for Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Dong Li, Hangyu Mao, Jingqing Ruan, Xiaotian Hao","submitted_at":"2023-07-28T12:41:36Z","abstract_excerpt":"Multi-agent systems require effective coordination between groups and individuals to achieve common goals. However, current multi-agent reinforcement learning (MARL) methods primarily focus on improving individual policies and do not adequately address group-level policies, which leads to weak cooperation. To address this issue, we propose a novel Consensus-oriented Strategy (CoS) that emphasizes group and individual policies simultaneously. Specifically, CoS comprises two main components: (a) the vector quantized group consensus module, which extracts discrete latent embeddings that represent"},"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":"2307.15530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-07-28T12:41:36Z","cross_cats_sorted":[],"title_canon_sha256":"423c4a4b19508334cdb7c02de56cff2041565b1be9f7451c5788af20a0de4520","abstract_canon_sha256":"25cb4a4e005be58b9557822f57734488ce026c771e513e65298f7dd981ac8bf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:36.434711Z","signature_b64":"pi1lblCioPGibo/58SJURz1CTcUxXsg4DMc77Vfk7/1pcPS5LE12HwKvX7R3teFWRch+NVdJ/z+2rPPZNk/8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eb2931e461124ebc665dac252497e2eaf7f3436518c8ed8a4a0a1093350588a","last_reissued_at":"2026-07-05T06:35:36.434348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:36.434348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Collaborate by Grouping: a Consensus-oriented Strategy for Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Dong Li, Hangyu Mao, Jingqing Ruan, Xiaotian Hao","submitted_at":"2023-07-28T12:41:36Z","abstract_excerpt":"Multi-agent systems require effective coordination between groups and individuals to achieve common goals. However, current multi-agent reinforcement learning (MARL) methods primarily focus on improving individual policies and do not adequately address group-level policies, which leads to weak cooperation. To address this issue, we propose a novel Consensus-oriented Strategy (CoS) that emphasizes group and individual policies simultaneously. Specifically, CoS comprises two main components: (a) the vector quantized group consensus module, which extracts discrete latent embeddings that represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15530","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/2307.15530/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":"2307.15530","created_at":"2026-07-05T06:35:36.434416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15530v1","created_at":"2026-07-05T06:35:36.434416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15530","created_at":"2026-07-05T06:35:36.434416+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2ZJGHSGCESO","created_at":"2026-07-05T06:35:36.434416+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2ZJGHSGCESOXRTF","created_at":"2026-07-05T06:35:36.434416+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2ZJGHSG","created_at":"2026-07-05T06:35:36.434416+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/T2ZJGHSGCESOXRTF3LBFESL6F2","json":"https://pith.science/pith/T2ZJGHSGCESOXRTF3LBFESL6F2.json","graph_json":"https://pith.science/api/pith-number/T2ZJGHSGCESOXRTF3LBFESL6F2/graph.json","events_json":"https://pith.science/api/pith-number/T2ZJGHSGCESOXRTF3LBFESL6F2/events.json","paper":"https://pith.science/paper/T2ZJGHSG"},"agent_actions":{"view_html":"https://pith.science/pith/T2ZJGHSGCESOXRTF3LBFESL6F2","download_json":"https://pith.science/pith/T2ZJGHSGCESOXRTF3LBFESL6F2.json","view_paper":"https://pith.science/paper/T2ZJGHSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15530&json=true","fetch_graph":"https://pith.science/api/pith-number/T2ZJGHSGCESOXRTF3LBFESL6F2/graph.json","fetch_events":"https://pith.science/api/pith-number/T2ZJGHSGCESOXRTF3LBFESL6F2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2ZJGHSGCESOXRTF3LBFESL6F2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2ZJGHSGCESOXRTF3LBFESL6F2/action/storage_attestation","attest_author":"https://pith.science/pith/T2ZJGHSGCESOXRTF3LBFESL6F2/action/author_attestation","sign_citation":"https://pith.science/pith/T2ZJGHSGCESOXRTF3LBFESL6F2/action/citation_signature","submit_replication":"https://pith.science/pith/T2ZJGHSGCESOXRTF3LBFESL6F2/action/replication_record"}},"created_at":"2026-07-05T06:35:36.434416+00:00","updated_at":"2026-07-05T06:35:36.434416+00:00"}