{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YG66OH2X54GFOQVMGDRPOAA4RN","short_pith_number":"pith:YG66OH2X","schema_version":"1.0","canonical_sha256":"c1bde71f57ef0c5742ac30e2f7001c8b70b3d87f8e037c2b3eb92c3ac61ca4d0","source":{"kind":"arxiv","id":"2008.03444","version":3},"attestation_state":"computed","paper":{"title":"Hierarchical Reinforcement Learning in StarCraft II with Human Expertise in Subgoals Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akshay Narayan, Pengfei Wei, Tiancheng Huang, Tze-Yun Leong, Xinyi Xu","submitted_at":"2020-08-08T04:56:30Z","abstract_excerpt":"This work is inspired by recent advances in hierarchical reinforcement learning (HRL) (Barto and Mahadevan 2003; Hengst 2010), and improvements in learning efficiency from heuristic-based subgoal selection, experience replay (Lin 1993; Andrychowicz et al. 2017), and task-based curriculum learning (Bengio et al. 2009; Zaremba and Sutskever 2014). We propose a new method to integrate HRL, experience replay and effective subgoal selection through an implicit curriculum design based on human expertise to support sample-efficient learning and enhance interpretability of the agent's behavior. Human "},"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":"2008.03444","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-08T04:56:30Z","cross_cats_sorted":[],"title_canon_sha256":"7e5e6d92d81f364f0a2a5942c81d8a141a0692cd6f55c77f45e7402358ebe6a0","abstract_canon_sha256":"aafd49bbed8d0303a153bfd6f8d1cb544aa4e4a67e79b1fb964e0b5d8f64809e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:39.467867Z","signature_b64":"1qNGlfV6/7PrME0/IS0xAmCYAHXFDizO9l2VcIoKbhxfJQBWUQx7Fsz79pNxyk6go6tOWlDCtO3H7Ic34nQtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1bde71f57ef0c5742ac30e2f7001c8b70b3d87f8e037c2b3eb92c3ac61ca4d0","last_reissued_at":"2026-07-05T01:38:39.467488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:39.467488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Reinforcement Learning in StarCraft II with Human Expertise in Subgoals Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akshay Narayan, Pengfei Wei, Tiancheng Huang, Tze-Yun Leong, Xinyi Xu","submitted_at":"2020-08-08T04:56:30Z","abstract_excerpt":"This work is inspired by recent advances in hierarchical reinforcement learning (HRL) (Barto and Mahadevan 2003; Hengst 2010), and improvements in learning efficiency from heuristic-based subgoal selection, experience replay (Lin 1993; Andrychowicz et al. 2017), and task-based curriculum learning (Bengio et al. 2009; Zaremba and Sutskever 2014). We propose a new method to integrate HRL, experience replay and effective subgoal selection through an implicit curriculum design based on human expertise to support sample-efficient learning and enhance interpretability of the agent's behavior. Human "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03444","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/2008.03444/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":"2008.03444","created_at":"2026-07-05T01:38:39.467548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03444v3","created_at":"2026-07-05T01:38:39.467548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03444","created_at":"2026-07-05T01:38:39.467548+00:00"},{"alias_kind":"pith_short_12","alias_value":"YG66OH2X54GF","created_at":"2026-07-05T01:38:39.467548+00:00"},{"alias_kind":"pith_short_16","alias_value":"YG66OH2X54GFOQVM","created_at":"2026-07-05T01:38:39.467548+00:00"},{"alias_kind":"pith_short_8","alias_value":"YG66OH2X","created_at":"2026-07-05T01:38:39.467548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18867","citing_title":"Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YG66OH2X54GFOQVMGDRPOAA4RN","json":"https://pith.science/pith/YG66OH2X54GFOQVMGDRPOAA4RN.json","graph_json":"https://pith.science/api/pith-number/YG66OH2X54GFOQVMGDRPOAA4RN/graph.json","events_json":"https://pith.science/api/pith-number/YG66OH2X54GFOQVMGDRPOAA4RN/events.json","paper":"https://pith.science/paper/YG66OH2X"},"agent_actions":{"view_html":"https://pith.science/pith/YG66OH2X54GFOQVMGDRPOAA4RN","download_json":"https://pith.science/pith/YG66OH2X54GFOQVMGDRPOAA4RN.json","view_paper":"https://pith.science/paper/YG66OH2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03444&json=true","fetch_graph":"https://pith.science/api/pith-number/YG66OH2X54GFOQVMGDRPOAA4RN/graph.json","fetch_events":"https://pith.science/api/pith-number/YG66OH2X54GFOQVMGDRPOAA4RN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YG66OH2X54GFOQVMGDRPOAA4RN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YG66OH2X54GFOQVMGDRPOAA4RN/action/storage_attestation","attest_author":"https://pith.science/pith/YG66OH2X54GFOQVMGDRPOAA4RN/action/author_attestation","sign_citation":"https://pith.science/pith/YG66OH2X54GFOQVMGDRPOAA4RN/action/citation_signature","submit_replication":"https://pith.science/pith/YG66OH2X54GFOQVMGDRPOAA4RN/action/replication_record"}},"created_at":"2026-07-05T01:38:39.467548+00:00","updated_at":"2026-07-05T01:38:39.467548+00:00"}