{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BADXUWFIKMYOOZ5FPEOGBVSUVL","short_pith_number":"pith:BADXUWFI","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"},"canonical_sha256":"08077a58a85330e767a5791c60d654aac6c8446a127fa436d2b007594773fb27","source":{"kind":"arxiv","id":"2304.09870","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.09870","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2304.09870v2","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09870","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"BADXUWFIKMYO","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"BADXUWFIKMYOOZ5F","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"BADXUWFI","created_at":"2026-07-05T07:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BADXUWFIKMYOOZ5FPEOGBVSUVL","target":"record","payload":{"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"},"canonical_sha256":"08077a58a85330e767a5791c60d654aac6c8446a127fa436d2b007594773fb27","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"},"source_kind":"arxiv","source_id":"2304.09870","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lnxCezqpa68e07HU5mql9eKSnR1oXd10EBPe6hPlmr4vQmGwj3Ixoeg9UxbHhL6Olm57VXabZ0hSRAqXhwVCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:03:05.929174Z"},"content_sha256":"8286e04c6b9bc6332a36244f5db3cf2c20c33ca5f242d3ff47a3e17e3493d18a","schema_version":"1.0","event_id":"sha256:8286e04c6b9bc6332a36244f5db3cf2c20c33ca5f242d3ff47a3e17e3493d18a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BADXUWFIKMYOOZ5FPEOGBVSUVL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3LiXMFFlPtVk2D2RuLuoxICucMPcCF/24dyIOqDbpPB+DF3PhXkza8ppbZmKlgmwJ48AIuE+cy9Ey+ZRCt8iDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:03:05.929673Z"},"content_sha256":"9cdad8a00242ed01faf58533f6df5b9d6def5a0673cdfd853856bb17f2fafb21","schema_version":"1.0","event_id":"sha256:9cdad8a00242ed01faf58533f6df5b9d6def5a0673cdfd853856bb17f2fafb21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/bundle.json","state_url":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T08:03:05Z","links":{"resolver":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL","bundle":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/bundle.json","state":"https://pith.science/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BADXUWFIKMYOOZ5FPEOGBVSUVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BADXUWFIKMYOOZ5FPEOGBVSUVL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"27aa686edce8e85bf7d48c1c09536bf78a72f337812b816c15a0b83679329caf","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-19T05:08:02Z","title_canon_sha256":"462b833af1243f467af6d5fa273a344f76f10eb53a52912d78daadf12539784e"},"schema_version":"1.0","source":{"id":"2304.09870","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.09870","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2304.09870v2","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09870","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"BADXUWFIKMYO","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"BADXUWFIKMYOOZ5F","created_at":"2026-07-05T07:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"BADXUWFI","created_at":"2026-07-05T07:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:9cdad8a00242ed01faf58533f6df5b9d6def5a0673cdfd853856bb17f2fafb21","target":"graph","created_at":"2026-07-05T07:28:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.09870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jakub Grudzien Kuba, Jiaming Ji, Siyi Hu, Xidong Feng, Yaodong Yang, Yifan Zhong","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-19T05:08:02Z","title":"Heterogeneous-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09870","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8286e04c6b9bc6332a36244f5db3cf2c20c33ca5f242d3ff47a3e17e3493d18a","target":"record","created_at":"2026-07-05T07:28:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"27aa686edce8e85bf7d48c1c09536bf78a72f337812b816c15a0b83679329caf","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-19T05:08:02Z","title_canon_sha256":"462b833af1243f467af6d5fa273a344f76f10eb53a52912d78daadf12539784e"},"schema_version":"1.0","source":{"id":"2304.09870","kind":"arxiv","version":2}},"canonical_sha256":"08077a58a85330e767a5791c60d654aac6c8446a127fa436d2b007594773fb27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08077a58a85330e767a5791c60d654aac6c8446a127fa436d2b007594773fb27","first_computed_at":"2026-07-05T07:28:28.043060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:28.043060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OLgW95kezOJGRtf8VBZ5rp/ub898zzQkLaQ6pch4gT4PM881F1EYOugQY7p+9js/gLZUldEvEncn3+xoonzhDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:28.043497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.09870","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8286e04c6b9bc6332a36244f5db3cf2c20c33ca5f242d3ff47a3e17e3493d18a","sha256:9cdad8a00242ed01faf58533f6df5b9d6def5a0673cdfd853856bb17f2fafb21"],"state_sha256":"b0f85f4f211b3c9977b59aa80b468b5e271413ee0375aaccb09d5a5acd540a86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FIoOf3CsA5rDKeHT8nQ1SJLI2ZhJYzrCtuVTo08abZobalKP2b3QPNx1l7k9P2PcVhgrOMQ1WNdLRL9UO5xDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:03:05.933975Z","bundle_sha256":"b4acc95fcff1ca07f87540a437e71f9bd1306faf394c123c1ce8651f6cb732da"}}