{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AGEQKAHVZ7KAPIW7IQF22QLOEN","short_pith_number":"pith:AGEQKAHV","schema_version":"1.0","canonical_sha256":"01890500f5cfd407a2df440bad416e23765680c38e3fd59da051c15ac5f85a5f","source":{"kind":"arxiv","id":"2403.03172","version":1},"attestation_state":"computed","paper":{"title":"Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Deheng Ye, Fengming Zhu, Haobo Fu, Kaiwen Zhu, Liangzhou Wang, Qiang Fu, Shujie Zhang, Wei Yang, Xinghu Yao","submitted_at":"2024-03-05T18:07:34Z","abstract_excerpt":"Reaching consensus is key to multi-agent coordination. To accomplish a cooperative task, agents need to coherently select optimal joint actions to maximize the team reward. However, current cooperative multi-agent reinforcement learning (MARL) methods usually do not explicitly take consensus into consideration, which may cause miscoordination problem. In this paper, we propose a model-based consensus mechanism to explicitly coordinate multiple agents. The proposed Multi-agent Goal Imagination (MAGI) framework guides agents to reach consensus with an Imagined common goal. The common goal is an "},"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":"2403.03172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-05T18:07:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cd022cfaab46e535ed29ccc7fae64b6be995068d20887e39310db19c83589186","abstract_canon_sha256":"10dc0bc73fa8785e44760c3602d3654e17f5e0ea0fc52b000c485d1ffc7b1dea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:36.864258Z","signature_b64":"h8HcCmxRYgJrzJF8Ay3WXWcsHBBlBM6D8J6fhmaGJd2L8X2BQ1A2h/t1FWzcNrDsBjbtSU4mW9evFfsomf+RBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01890500f5cfd407a2df440bad416e23765680c38e3fd59da051c15ac5f85a5f","last_reissued_at":"2026-07-05T07:52:36.863850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:36.863850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Deheng Ye, Fengming Zhu, Haobo Fu, Kaiwen Zhu, Liangzhou Wang, Qiang Fu, Shujie Zhang, Wei Yang, Xinghu Yao","submitted_at":"2024-03-05T18:07:34Z","abstract_excerpt":"Reaching consensus is key to multi-agent coordination. To accomplish a cooperative task, agents need to coherently select optimal joint actions to maximize the team reward. However, current cooperative multi-agent reinforcement learning (MARL) methods usually do not explicitly take consensus into consideration, which may cause miscoordination problem. In this paper, we propose a model-based consensus mechanism to explicitly coordinate multiple agents. The proposed Multi-agent Goal Imagination (MAGI) framework guides agents to reach consensus with an Imagined common goal. The common goal is an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03172","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/2403.03172/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":"2403.03172","created_at":"2026-07-05T07:52:36.863907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03172v1","created_at":"2026-07-05T07:52:36.863907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03172","created_at":"2026-07-05T07:52:36.863907+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGEQKAHVZ7KA","created_at":"2026-07-05T07:52:36.863907+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGEQKAHVZ7KAPIW7","created_at":"2026-07-05T07:52:36.863907+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGEQKAHV","created_at":"2026-07-05T07:52:36.863907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12497","citing_title":"Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGEQKAHVZ7KAPIW7IQF22QLOEN","json":"https://pith.science/pith/AGEQKAHVZ7KAPIW7IQF22QLOEN.json","graph_json":"https://pith.science/api/pith-number/AGEQKAHVZ7KAPIW7IQF22QLOEN/graph.json","events_json":"https://pith.science/api/pith-number/AGEQKAHVZ7KAPIW7IQF22QLOEN/events.json","paper":"https://pith.science/paper/AGEQKAHV"},"agent_actions":{"view_html":"https://pith.science/pith/AGEQKAHVZ7KAPIW7IQF22QLOEN","download_json":"https://pith.science/pith/AGEQKAHVZ7KAPIW7IQF22QLOEN.json","view_paper":"https://pith.science/paper/AGEQKAHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03172&json=true","fetch_graph":"https://pith.science/api/pith-number/AGEQKAHVZ7KAPIW7IQF22QLOEN/graph.json","fetch_events":"https://pith.science/api/pith-number/AGEQKAHVZ7KAPIW7IQF22QLOEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGEQKAHVZ7KAPIW7IQF22QLOEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGEQKAHVZ7KAPIW7IQF22QLOEN/action/storage_attestation","attest_author":"https://pith.science/pith/AGEQKAHVZ7KAPIW7IQF22QLOEN/action/author_attestation","sign_citation":"https://pith.science/pith/AGEQKAHVZ7KAPIW7IQF22QLOEN/action/citation_signature","submit_replication":"https://pith.science/pith/AGEQKAHVZ7KAPIW7IQF22QLOEN/action/replication_record"}},"created_at":"2026-07-05T07:52:36.863907+00:00","updated_at":"2026-07-05T07:52:36.863907+00:00"}