{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JUCMAUYYGJU76ME2WNR577J7GH","short_pith_number":"pith:JUCMAUYY","schema_version":"1.0","canonical_sha256":"4d04c053183269ff309ab363dffd3f31c0e7b0c29a72f3c11629476cb0ee50dc","source":{"kind":"arxiv","id":"1809.09095","version":2},"attestation_state":"computed","paper":{"title":"On Reinforcement Learning for Full-length Game of StarCraft","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ruo-Ze Liu, Tong Lu, Yang Yu, Yi Zhang, Zhen-Jia Pang, Zhou-Yu Meng","submitted_at":"2018-09-23T15:48:28Z","abstract_excerpt":"StarCraft II poses a grand challenge for reinforcement learning. The main difficulties of it include huge state and action space and a long-time horizon. In this paper, we investigate a hierarchical reinforcement learning approach for StarCraft II. The hierarchy involves two levels of abstraction. One is the macro-action automatically extracted from expert's trajectories, which reduces the action space in an order of magnitude yet remains effective. The other is a two-layer hierarchical architecture which is modular and easy to scale, enabling a curriculum transferring from simpler tasks to mo"},"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":"1809.09095","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-23T15:48:28Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d3ff5f26fd4a56a9ce376766f5d9a3f2eff255508d425fc2e5a7a906552d790d","abstract_canon_sha256":"b0c3502154651ee13c887993d186d22c8dc37ec76913334bd5e065c158609564"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:53.767867Z","signature_b64":"bhKpyefu+kr6TmmjC062rqWFejO6G9iF3GBl4qga2m0ocbrxldZ+VyERrE4tRcIjOxQnByFqMUgM8Y5+KQdtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d04c053183269ff309ab363dffd3f31c0e7b0c29a72f3c11629476cb0ee50dc","last_reissued_at":"2026-05-17T23:54:53.767274Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:53.767274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Reinforcement Learning for Full-length Game of StarCraft","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ruo-Ze Liu, Tong Lu, Yang Yu, Yi Zhang, Zhen-Jia Pang, Zhou-Yu Meng","submitted_at":"2018-09-23T15:48:28Z","abstract_excerpt":"StarCraft II poses a grand challenge for reinforcement learning. The main difficulties of it include huge state and action space and a long-time horizon. In this paper, we investigate a hierarchical reinforcement learning approach for StarCraft II. The hierarchy involves two levels of abstraction. One is the macro-action automatically extracted from expert's trajectories, which reduces the action space in an order of magnitude yet remains effective. The other is a two-layer hierarchical architecture which is modular and easy to scale, enabling a curriculum transferring from simpler tasks to mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09095","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":""},"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":"1809.09095","created_at":"2026-05-17T23:54:53.767368+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.09095v2","created_at":"2026-05-17T23:54:53.767368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09095","created_at":"2026-05-17T23:54:53.767368+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUCMAUYYGJU7","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUCMAUYYGJU76ME2","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUCMAUYY","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10124","citing_title":"On Multi-Agent Learning in Team Sports Games","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07752","citing_title":"MIMIC-Py: An Extensible Tool for Personality-Driven Automated Game Testing with Large Language Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUCMAUYYGJU76ME2WNR577J7GH","json":"https://pith.science/pith/JUCMAUYYGJU76ME2WNR577J7GH.json","graph_json":"https://pith.science/api/pith-number/JUCMAUYYGJU76ME2WNR577J7GH/graph.json","events_json":"https://pith.science/api/pith-number/JUCMAUYYGJU76ME2WNR577J7GH/events.json","paper":"https://pith.science/paper/JUCMAUYY"},"agent_actions":{"view_html":"https://pith.science/pith/JUCMAUYYGJU76ME2WNR577J7GH","download_json":"https://pith.science/pith/JUCMAUYYGJU76ME2WNR577J7GH.json","view_paper":"https://pith.science/paper/JUCMAUYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.09095&json=true","fetch_graph":"https://pith.science/api/pith-number/JUCMAUYYGJU76ME2WNR577J7GH/graph.json","fetch_events":"https://pith.science/api/pith-number/JUCMAUYYGJU76ME2WNR577J7GH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUCMAUYYGJU76ME2WNR577J7GH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUCMAUYYGJU76ME2WNR577J7GH/action/storage_attestation","attest_author":"https://pith.science/pith/JUCMAUYYGJU76ME2WNR577J7GH/action/author_attestation","sign_citation":"https://pith.science/pith/JUCMAUYYGJU76ME2WNR577J7GH/action/citation_signature","submit_replication":"https://pith.science/pith/JUCMAUYYGJU76ME2WNR577J7GH/action/replication_record"}},"created_at":"2026-05-17T23:54:53.767368+00:00","updated_at":"2026-05-17T23:54:53.767368+00:00"}