{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JUCMAUYYGJU76ME2WNR577J7GH","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":"b0c3502154651ee13c887993d186d22c8dc37ec76913334bd5e065c158609564","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-23T15:48:28Z","title_canon_sha256":"d3ff5f26fd4a56a9ce376766f5d9a3f2eff255508d425fc2e5a7a906552d790d"},"schema_version":"1.0","source":{"id":"1809.09095","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.09095","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"1809.09095v2","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09095","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"JUCMAUYYGJU7","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JUCMAUYYGJU76ME2","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JUCMAUYY","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:a0dd589e333ded090de04a1c64a395b03446dd54be18f446af96f0bd2dc4e6c2","target":"graph","created_at":"2026-05-17T23:54:53Z","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"},"paper":{"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","authors_text":"Ruo-Ze Liu, Tong Lu, Yang Yu, Yi Zhang, Zhen-Jia Pang, Zhou-Yu Meng","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-23T15:48:28Z","title":"On Reinforcement Learning for Full-length Game of StarCraft"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09095","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:eb6e7ba7716dfd9d0892a768345702fb351221f1253c651e15a0d0ca92b41565","target":"record","created_at":"2026-05-17T23:54:53Z","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":"b0c3502154651ee13c887993d186d22c8dc37ec76913334bd5e065c158609564","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-23T15:48:28Z","title_canon_sha256":"d3ff5f26fd4a56a9ce376766f5d9a3f2eff255508d425fc2e5a7a906552d790d"},"schema_version":"1.0","source":{"id":"1809.09095","kind":"arxiv","version":2}},"canonical_sha256":"4d04c053183269ff309ab363dffd3f31c0e7b0c29a72f3c11629476cb0ee50dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d04c053183269ff309ab363dffd3f31c0e7b0c29a72f3c11629476cb0ee50dc","first_computed_at":"2026-05-17T23:54:53.767274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:53.767274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bhKpyefu+kr6TmmjC062rqWFejO6G9iF3GBl4qga2m0ocbrxldZ+VyERrE4tRcIjOxQnByFqMUgM8Y5+KQdtBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:53.767867Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.09095","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb6e7ba7716dfd9d0892a768345702fb351221f1253c651e15a0d0ca92b41565","sha256:a0dd589e333ded090de04a1c64a395b03446dd54be18f446af96f0bd2dc4e6c2"],"state_sha256":"e322d748e369d7b75476a7c9fb111e9edf44522b56bb5066b4a68179df634604"}