{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GJVHBVXSIYFX2TAMZTOSOHLGOD","short_pith_number":"pith:GJVHBVXS","schema_version":"1.0","canonical_sha256":"326a70d6f2460b7d4c0cccdd271d6670df7dcd5376773a45252ed0a78c2ebbe5","source":{"kind":"arxiv","id":"2003.08039","version":3},"attestation_state":"computed","paper":{"title":"ROMA: Multi-Agent Reinforcement Learning with Emergent Roles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Chongjie Zhang, Heng Dong, Tonghan Wang, Victor Lesser","submitted_at":"2020-03-18T04:29:42Z","abstract_excerpt":"The role concept provides a useful tool to design and understand complex multi-agent systems, which allows agents with a similar role to share similar behaviors. However, existing role-based methods use prior domain knowledge and predefine role structures and behaviors. In contrast, multi-agent reinforcement learning (MARL) provides flexibility and adaptability, but less efficiency in complex tasks. In this paper, we synergize these two paradigms and propose a role-oriented MARL framework (ROMA). In this framework, roles are emergent, and agents with similar roles tend to share their learning "},"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":"2003.08039","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-03-18T04:29:42Z","cross_cats_sorted":[],"title_canon_sha256":"f500355d21930ab958768d1e82f14713439072bb38f5b99285cb2ee622379911","abstract_canon_sha256":"f27d8245a715b71f91f937521de43a18a4251b1ccab807b3a2d76b8d5c838fae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:13.744108Z","signature_b64":"znmT8eKBu1Aav9fkL4w7ztu7K/Mu2XGNpcDZXXn2RCE5UsyS7+nDcw0zquRKvNGS1B2A5dWr9tKgi9BqrtIGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"326a70d6f2460b7d4c0cccdd271d6670df7dcd5376773a45252ed0a78c2ebbe5","last_reissued_at":"2026-07-05T01:16:13.743572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:13.743572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ROMA: Multi-Agent Reinforcement Learning with Emergent Roles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Chongjie Zhang, Heng Dong, Tonghan Wang, Victor Lesser","submitted_at":"2020-03-18T04:29:42Z","abstract_excerpt":"The role concept provides a useful tool to design and understand complex multi-agent systems, which allows agents with a similar role to share similar behaviors. However, existing role-based methods use prior domain knowledge and predefine role structures and behaviors. In contrast, multi-agent reinforcement learning (MARL) provides flexibility and adaptability, but less efficiency in complex tasks. In this paper, we synergize these two paradigms and propose a role-oriented MARL framework (ROMA). In this framework, roles are emergent, and agents with similar roles tend to share their learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08039","kind":"arxiv","version":3},"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/2003.08039/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":"2003.08039","created_at":"2026-07-05T01:16:13.743643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.08039v3","created_at":"2026-07-05T01:16:13.743643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08039","created_at":"2026-07-05T01:16:13.743643+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJVHBVXSIYFX","created_at":"2026-07-05T01:16:13.743643+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJVHBVXSIYFX2TAM","created_at":"2026-07-05T01:16:13.743643+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJVHBVXS","created_at":"2026-07-05T01:16:13.743643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11880","citing_title":"Adaptive TD-Lambda for Cooperative Multi-agent Reinforcement Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09028","citing_title":"Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17745","citing_title":"HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Execution","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJVHBVXSIYFX2TAMZTOSOHLGOD","json":"https://pith.science/pith/GJVHBVXSIYFX2TAMZTOSOHLGOD.json","graph_json":"https://pith.science/api/pith-number/GJVHBVXSIYFX2TAMZTOSOHLGOD/graph.json","events_json":"https://pith.science/api/pith-number/GJVHBVXSIYFX2TAMZTOSOHLGOD/events.json","paper":"https://pith.science/paper/GJVHBVXS"},"agent_actions":{"view_html":"https://pith.science/pith/GJVHBVXSIYFX2TAMZTOSOHLGOD","download_json":"https://pith.science/pith/GJVHBVXSIYFX2TAMZTOSOHLGOD.json","view_paper":"https://pith.science/paper/GJVHBVXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.08039&json=true","fetch_graph":"https://pith.science/api/pith-number/GJVHBVXSIYFX2TAMZTOSOHLGOD/graph.json","fetch_events":"https://pith.science/api/pith-number/GJVHBVXSIYFX2TAMZTOSOHLGOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJVHBVXSIYFX2TAMZTOSOHLGOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJVHBVXSIYFX2TAMZTOSOHLGOD/action/storage_attestation","attest_author":"https://pith.science/pith/GJVHBVXSIYFX2TAMZTOSOHLGOD/action/author_attestation","sign_citation":"https://pith.science/pith/GJVHBVXSIYFX2TAMZTOSOHLGOD/action/citation_signature","submit_replication":"https://pith.science/pith/GJVHBVXSIYFX2TAMZTOSOHLGOD/action/replication_record"}},"created_at":"2026-07-05T01:16:13.743643+00:00","updated_at":"2026-07-05T01:16:13.743643+00:00"}