{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YG66OH2X54GFOQVMGDRPOAA4RN","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":"aafd49bbed8d0303a153bfd6f8d1cb544aa4e4a67e79b1fb964e0b5d8f64809e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-08T04:56:30Z","title_canon_sha256":"7e5e6d92d81f364f0a2a5942c81d8a141a0692cd6f55c77f45e7402358ebe6a0"},"schema_version":"1.0","source":{"id":"2008.03444","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03444","created_at":"2026-07-05T01:38:39Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03444v3","created_at":"2026-07-05T01:38:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03444","created_at":"2026-07-05T01:38:39Z"},{"alias_kind":"pith_short_12","alias_value":"YG66OH2X54GF","created_at":"2026-07-05T01:38:39Z"},{"alias_kind":"pith_short_16","alias_value":"YG66OH2X54GFOQVM","created_at":"2026-07-05T01:38:39Z"},{"alias_kind":"pith_short_8","alias_value":"YG66OH2X","created_at":"2026-07-05T01:38:39Z"}],"graph_snapshots":[{"event_id":"sha256:7e6b082840cf353b849305b031be2d93b6f837e93bf00b4df2f833c776b7707a","target":"graph","created_at":"2026-07-05T01:38:39Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.03444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Akshay Narayan, Pengfei Wei, Tiancheng Huang, Tze-Yun Leong, Xinyi Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-08T04:56:30Z","title":"Hierarchical Reinforcement Learning in StarCraft II with Human Expertise in Subgoals Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03444","kind":"arxiv","version":3},"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":"sha256:30197e9b4c6e5a0a427fd9c30a370a71a88c5824c70afff53608535bb5b02040","target":"record","created_at":"2026-07-05T01:38:39Z","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":"aafd49bbed8d0303a153bfd6f8d1cb544aa4e4a67e79b1fb964e0b5d8f64809e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-08T04:56:30Z","title_canon_sha256":"7e5e6d92d81f364f0a2a5942c81d8a141a0692cd6f55c77f45e7402358ebe6a0"},"schema_version":"1.0","source":{"id":"2008.03444","kind":"arxiv","version":3}},"canonical_sha256":"c1bde71f57ef0c5742ac30e2f7001c8b70b3d87f8e037c2b3eb92c3ac61ca4d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1bde71f57ef0c5742ac30e2f7001c8b70b3d87f8e037c2b3eb92c3ac61ca4d0","first_computed_at":"2026-07-05T01:38:39.467488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:38:39.467488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1qNGlfV6/7PrME0/IS0xAmCYAHXFDizO9l2VcIoKbhxfJQBWUQx7Fsz79pNxyk6go6tOWlDCtO3H7Ic34nQtCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:38:39.467867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.03444","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30197e9b4c6e5a0a427fd9c30a370a71a88c5824c70afff53608535bb5b02040","sha256:7e6b082840cf353b849305b031be2d93b6f837e93bf00b4df2f833c776b7707a"],"state_sha256":"633fa58d3d29b6f9ce14f18b0b22eb4af361b76b534f10c034f7fd8fd3546518"}