{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O5LWE76IQOHNZUTKFX3NF22QLI","short_pith_number":"pith:O5LWE76I","schema_version":"1.0","canonical_sha256":"7757627fc8838edcd26a2df6d2eb505a175d22d2d313c7052d1d06b4a9400ee9","source":{"kind":"arxiv","id":"2404.03869","version":2},"attestation_state":"computed","paper":{"title":"Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Daming Shi, Junjie Yu, Wenhui Fan, Xudong Guo","submitted_at":"2024-04-05T03:02:57Z","abstract_excerpt":"The emergence of multi-agent reinforcement learning (MARL) is significantly transforming various fields like autonomous vehicle networks. However, real-world multi-agent systems typically contain multiple roles, and the scale of these systems dynamically fluctuates. Consequently, in order to achieve zero-shot scalable collaboration, it is essential that strategies for different roles can be updated flexibly according to the scales, which is still a challenge for current MARL frameworks. To address this, we propose a novel MARL framework named Scalable and Heterogeneous Proximal Policy Optimiza"},"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":"2404.03869","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T03:02:57Z","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"ddb41523ce22db14db21838ee82b53e7a5912f3a189eada98c0a3ff3858ff272","abstract_canon_sha256":"c7e422eecc404326337f168bb5f8d6448cf96e0df39b9562b6c5155db1196930"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:31.654055Z","signature_b64":"NJIx2Ac4h0ia4uiaBUh9CVYmmynyTx0lXjyikubXzl6uDsy9mxk+adlXgR9CvBCTre8czAZTFxzrp1B3ApKJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7757627fc8838edcd26a2df6d2eb505a175d22d2d313c7052d1d06b4a9400ee9","last_reissued_at":"2026-07-05T09:14:31.653521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:31.653521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Daming Shi, Junjie Yu, Wenhui Fan, Xudong Guo","submitted_at":"2024-04-05T03:02:57Z","abstract_excerpt":"The emergence of multi-agent reinforcement learning (MARL) is significantly transforming various fields like autonomous vehicle networks. However, real-world multi-agent systems typically contain multiple roles, and the scale of these systems dynamically fluctuates. Consequently, in order to achieve zero-shot scalable collaboration, it is essential that strategies for different roles can be updated flexibly according to the scales, which is still a challenge for current MARL frameworks. To address this, we propose a novel MARL framework named Scalable and Heterogeneous Proximal Policy Optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03869","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/2404.03869/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":"2404.03869","created_at":"2026-07-05T09:14:31.653597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03869v2","created_at":"2026-07-05T09:14:31.653597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03869","created_at":"2026-07-05T09:14:31.653597+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5LWE76IQOHN","created_at":"2026-07-05T09:14:31.653597+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5LWE76IQOHNZUTK","created_at":"2026-07-05T09:14:31.653597+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5LWE76I","created_at":"2026-07-05T09:14:31.653597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.13657","citing_title":"Why Do Multi-Agent LLM Systems Fail?","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06825","citing_title":"Randomness is sometimes necessary for coordination","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI","json":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI.json","graph_json":"https://pith.science/api/pith-number/O5LWE76IQOHNZUTKFX3NF22QLI/graph.json","events_json":"https://pith.science/api/pith-number/O5LWE76IQOHNZUTKFX3NF22QLI/events.json","paper":"https://pith.science/paper/O5LWE76I"},"agent_actions":{"view_html":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI","download_json":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI.json","view_paper":"https://pith.science/paper/O5LWE76I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03869&json=true","fetch_graph":"https://pith.science/api/pith-number/O5LWE76IQOHNZUTKFX3NF22QLI/graph.json","fetch_events":"https://pith.science/api/pith-number/O5LWE76IQOHNZUTKFX3NF22QLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI/action/storage_attestation","attest_author":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI/action/author_attestation","sign_citation":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI/action/citation_signature","submit_replication":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI/action/replication_record"}},"created_at":"2026-07-05T09:14:31.653597+00:00","updated_at":"2026-07-05T09:14:31.653597+00:00"}