{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KHDX3TESJKKTSYJ6EUGE4PKJ76","short_pith_number":"pith:KHDX3TES","schema_version":"1.0","canonical_sha256":"51c77dcc924a9539613e250c4e3d49ffadd852741f4755b032031257aab16f9a","source":{"kind":"arxiv","id":"2105.10211","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Joongheon Kim, Sungwon Yi, Won Joon Yun","submitted_at":"2021-05-21T09:05:25Z","abstract_excerpt":"In real-time strategy (RTS) game artificial intelligence research, various multi-agent deep reinforcement learning (MADRL) algorithms are widely and actively used nowadays. Most of the research is based on StarCraft II environment because it is the most well-known RTS games in world-wide. In our proposed MADRL-based algorithm, distributed MADRL is fundamentally used that is called QMIX. In addition to QMIX-based distributed computation, we consider state categorization which can reduce computational complexity significantly. Furthermore, self-attention mechanisms are used for identifying the r"},"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":"2105.10211","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-05-21T09:05:25Z","cross_cats_sorted":[],"title_canon_sha256":"dddf58f88ba873fe3a777b3d4fe41669769f79de18c60bbfa6ab9e945db5d2f1","abstract_canon_sha256":"18b6ea8715e8535454a76a15189fb11b3b083d5ad8b4b11fb6d828d3cb0757f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:08.905349Z","signature_b64":"L7GJfosngyfR9dVHGphWhCAUeKhfrCsB882GwRe2c9zoX79XoxCgu5RSjLUkxOMcLVaNWlF93HJi8etXThNnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51c77dcc924a9539613e250c4e3d49ffadd852741f4755b032031257aab16f9a","last_reissued_at":"2026-07-05T02:42:08.904942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:08.904942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Joongheon Kim, Sungwon Yi, Won Joon Yun","submitted_at":"2021-05-21T09:05:25Z","abstract_excerpt":"In real-time strategy (RTS) game artificial intelligence research, various multi-agent deep reinforcement learning (MADRL) algorithms are widely and actively used nowadays. Most of the research is based on StarCraft II environment because it is the most well-known RTS games in world-wide. In our proposed MADRL-based algorithm, distributed MADRL is fundamentally used that is called QMIX. In addition to QMIX-based distributed computation, we consider state categorization which can reduce computational complexity significantly. Furthermore, self-attention mechanisms are used for identifying the r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.10211","kind":"arxiv","version":1},"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/2105.10211/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":"2105.10211","created_at":"2026-07-05T02:42:08.904997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.10211v1","created_at":"2026-07-05T02:42:08.904997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.10211","created_at":"2026-07-05T02:42:08.904997+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHDX3TESJKKT","created_at":"2026-07-05T02:42:08.904997+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHDX3TESJKKTSYJ6","created_at":"2026-07-05T02:42:08.904997+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHDX3TES","created_at":"2026-07-05T02:42:08.904997+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/KHDX3TESJKKTSYJ6EUGE4PKJ76","json":"https://pith.science/pith/KHDX3TESJKKTSYJ6EUGE4PKJ76.json","graph_json":"https://pith.science/api/pith-number/KHDX3TESJKKTSYJ6EUGE4PKJ76/graph.json","events_json":"https://pith.science/api/pith-number/KHDX3TESJKKTSYJ6EUGE4PKJ76/events.json","paper":"https://pith.science/paper/KHDX3TES"},"agent_actions":{"view_html":"https://pith.science/pith/KHDX3TESJKKTSYJ6EUGE4PKJ76","download_json":"https://pith.science/pith/KHDX3TESJKKTSYJ6EUGE4PKJ76.json","view_paper":"https://pith.science/paper/KHDX3TES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.10211&json=true","fetch_graph":"https://pith.science/api/pith-number/KHDX3TESJKKTSYJ6EUGE4PKJ76/graph.json","fetch_events":"https://pith.science/api/pith-number/KHDX3TESJKKTSYJ6EUGE4PKJ76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHDX3TESJKKTSYJ6EUGE4PKJ76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHDX3TESJKKTSYJ6EUGE4PKJ76/action/storage_attestation","attest_author":"https://pith.science/pith/KHDX3TESJKKTSYJ6EUGE4PKJ76/action/author_attestation","sign_citation":"https://pith.science/pith/KHDX3TESJKKTSYJ6EUGE4PKJ76/action/citation_signature","submit_replication":"https://pith.science/pith/KHDX3TESJKKTSYJ6EUGE4PKJ76/action/replication_record"}},"created_at":"2026-07-05T02:42:08.904997+00:00","updated_at":"2026-07-05T02:42:08.904997+00:00"}