{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FHH5Q35PCHRNTMZICVFEYNULFQ","short_pith_number":"pith:FHH5Q35P","schema_version":"1.0","canonical_sha256":"29cfd86faf11e2d9b328154a4c368b2c012edebe5569794c22a7f803501e8080","source":{"kind":"arxiv","id":"2009.13161","version":3},"attestation_state":"computed","paper":{"title":"Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Douglas De Rizzo Meneghetti, Reinaldo Augusto da Costa Bianchi","submitted_at":"2020-09-28T09:15:04Z","abstract_excerpt":"This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting. The proposed network uses directed labeled graph representations for states, encodes feature vectors of different sizes for different entity classes, uses relational graph convolution layers to model different communication channels between entity types and learns distinct policies for different agent classes, sharing parameters wherever possible. Results have shown that specializing the communication channels between entity classes is a promisi"},"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":"2009.13161","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-09-28T09:15:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1dcf02998d613db023521f643911bade1e8839fa3a822986c65437692274f124","abstract_canon_sha256":"91784cefec52edcf79cfe9611f0b2ee6233e9ec66a367f535f9f42b22a70a7aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:50.986705Z","signature_b64":"L+VVKf8HyjaTBxiEPFNV5pXJR7xcGqvD7O4fqVjjquXvfhX3xqxo5wSPk3QZSaQkPqUTgbIlqVsLu9cpINBaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29cfd86faf11e2d9b328154a4c368b2c012edebe5569794c22a7f803501e8080","last_reissued_at":"2026-07-05T01:44:50.986264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:50.986264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Douglas De Rizzo Meneghetti, Reinaldo Augusto da Costa Bianchi","submitted_at":"2020-09-28T09:15:04Z","abstract_excerpt":"This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting. The proposed network uses directed labeled graph representations for states, encodes feature vectors of different sizes for different entity classes, uses relational graph convolution layers to model different communication channels between entity types and learns distinct policies for different agent classes, sharing parameters wherever possible. Results have shown that specializing the communication channels between entity classes is a promisi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13161","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/2009.13161/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":"2009.13161","created_at":"2026-07-05T01:44:50.986321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.13161v3","created_at":"2026-07-05T01:44:50.986321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13161","created_at":"2026-07-05T01:44:50.986321+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHH5Q35PCHRN","created_at":"2026-07-05T01:44:50.986321+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHH5Q35PCHRNTMZI","created_at":"2026-07-05T01:44:50.986321+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHH5Q35P","created_at":"2026-07-05T01:44:50.986321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20962","citing_title":"Heterogeneous Policy Networks for Composite Robot Team Communication and Coordination","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FHH5Q35PCHRNTMZICVFEYNULFQ","json":"https://pith.science/pith/FHH5Q35PCHRNTMZICVFEYNULFQ.json","graph_json":"https://pith.science/api/pith-number/FHH5Q35PCHRNTMZICVFEYNULFQ/graph.json","events_json":"https://pith.science/api/pith-number/FHH5Q35PCHRNTMZICVFEYNULFQ/events.json","paper":"https://pith.science/paper/FHH5Q35P"},"agent_actions":{"view_html":"https://pith.science/pith/FHH5Q35PCHRNTMZICVFEYNULFQ","download_json":"https://pith.science/pith/FHH5Q35PCHRNTMZICVFEYNULFQ.json","view_paper":"https://pith.science/paper/FHH5Q35P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.13161&json=true","fetch_graph":"https://pith.science/api/pith-number/FHH5Q35PCHRNTMZICVFEYNULFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FHH5Q35PCHRNTMZICVFEYNULFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHH5Q35PCHRNTMZICVFEYNULFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHH5Q35PCHRNTMZICVFEYNULFQ/action/storage_attestation","attest_author":"https://pith.science/pith/FHH5Q35PCHRNTMZICVFEYNULFQ/action/author_attestation","sign_citation":"https://pith.science/pith/FHH5Q35PCHRNTMZICVFEYNULFQ/action/citation_signature","submit_replication":"https://pith.science/pith/FHH5Q35PCHRNTMZICVFEYNULFQ/action/replication_record"}},"created_at":"2026-07-05T01:44:50.986321+00:00","updated_at":"2026-07-05T01:44:50.986321+00:00"}