{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BADXUWFIKMYOOZ5FPEOGBVSUVL","short_pith_number":"pith:BADXUWFI","schema_version":"1.0","canonical_sha256":"08077a58a85330e767a5791c60d654aac6c8446a127fa436d2b007594773fb27","source":{"kind":"arxiv","id":"2304.09870","version":2},"attestation_state":"computed","paper":{"title":"Heterogeneous-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Jakub Grudzien Kuba, Jiaming Ji, Siyi Hu, Xidong Feng, Yaodong Yang, Yifan Zhong","submitted_at":"2023-04-19T05:08:02Z","abstract_excerpt":"The necessity for cooperation among intelligent machines has popularised cooperative multi-agent reinforcement learning (MARL) in AI research. However, many research endeavours heavily rely on parameter sharing among agents, which confines them to only homogeneous-agent setting and leads to training instability and lack of convergence guarantees. To achieve effective cooperation in the general heterogeneous-agent setting, we propose Heterogeneous-Agent Reinforcement Learning (HARL) algorithms that resolve the aforementioned issues. Central to our findings are the multi-agent advantage decompos"},"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":"2304.09870","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-19T05:08:02Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"462b833af1243f467af6d5fa273a344f76f10eb53a52912d78daadf12539784e","abstract_canon_sha256":"27aa686edce8e85bf7d48c1c09536bf78a72f337812b816c15a0b83679329caf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:28.043497Z","signature_b64":"OLgW95kezOJGRtf8VBZ5rp/ub898zzQkLaQ6pch4gT4PM881F1EYOugQY7p+9js/gLZUldEvEncn3+xoonzhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08077a58a85330e767a5791c60d654aac6c8446a127fa436d2b007594773fb27","last_reissued_at":"2026-07-05T07:28:28.043060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:28.043060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Jakub Grudzien Kuba, Jiaming Ji, Siyi Hu, Xidong Feng, Yaodong Yang, Yifan Zhong","submitted_at":"2023-04-19T05:08:02Z","abstract_excerpt":"The necessity for cooperation among intelligent machines has popularised cooperative multi-agent reinforcement learning (MARL) in AI research. However, many research endeavours heavily rely on parameter sharing among agents, which confines them to only homogeneous-agent setting and leads to training instability and lack of convergence guarantees. To achieve effective cooperation in the general heterogeneous-agent setting, we propose Heterogeneous-Agent Reinforcement Learning (HARL) algorithms that resolve the aforementioned issues. Central to our findings are the multi-agent advantage decompos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09870","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/2304.09870/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":"2304.09870","created_at":"2026-07-05T07:28:28.043114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09870v2","created_at":"2026-07-05T07:28:28.043114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09870","created_at":"2026-07-05T07:28:28.043114+00:00"},{"alias_kind":"pith_short_12","alias_value":"BADXUWFIKMYO","created_at":"2026-07-05T07:28:28.043114+00:00"},{"alias_kind":"pith_short_16","alias_value":"BADXUWFIKMYOOZ5F","created_at":"2026-07-05T07:28:28.043114+00:00"},{"alias_kind":"pith_short_8","alias_value":"BADXUWFI","created_at":"2026-07-05T07:28:28.043114+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/BADXUWFIKMYOOZ5FPEOGBVSUVL","json":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL.json","graph_json":"https://pith.science/api/pith-number/BADXUWFIKMYOOZ5FPEOGBVSUVL/graph.json","events_json":"https://pith.science/api/pith-number/BADXUWFIKMYOOZ5FPEOGBVSUVL/events.json","paper":"https://pith.science/paper/BADXUWFI"},"agent_actions":{"view_html":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL","download_json":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL.json","view_paper":"https://pith.science/paper/BADXUWFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09870&json=true","fetch_graph":"https://pith.science/api/pith-number/BADXUWFIKMYOOZ5FPEOGBVSUVL/graph.json","fetch_events":"https://pith.science/api/pith-number/BADXUWFIKMYOOZ5FPEOGBVSUVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/action/storage_attestation","attest_author":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/action/author_attestation","sign_citation":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/action/citation_signature","submit_replication":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/action/replication_record"}},"created_at":"2026-07-05T07:28:28.043114+00:00","updated_at":"2026-07-05T07:28:28.043114+00:00"}