{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JOXEV44DDG2JQ57WDVM2O6OVBC","short_pith_number":"pith:JOXEV44D","schema_version":"1.0","canonical_sha256":"4bae4af38319b49877f61d59a779d508addf30820f30f9215545386e96d09e1e","source":{"kind":"arxiv","id":"2111.08857","version":1},"attestation_state":"computed","paper":{"title":"SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Chao Wang, Chengjie Wu, Dong Li, Hangyu Mao, Jianye Hao, Pingzhong Tang, Xiaotian Hao, Yihuan Mao, Yiming Lu","submitted_at":"2021-11-17T01:36:40Z","abstract_excerpt":"The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment interactions needed to solve the complex \\emph{ObtainDiamond} task with sparse rewards. To address the challenge, in this paper, we present \\textbf{SEIHAI}, a \\textbf{S}ample-\\textbf{e}ff\\textbf{i}cient \\textbf{H}ierarchical \\textbf{AI}, that fully takes advantage of the human demonstrations and the task structure. Specifically, we split the task into several sequentially dependent s"},"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":"2111.08857","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-17T01:36:40Z","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"36229040d46253289636171e5af8818a695477adb9df3a423a3987e16348bb23","abstract_canon_sha256":"c1a34487060d7e3f5938466b1c2298b64fdf09e265c9af79cf3c6a152db21581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:32:41.849967Z","signature_b64":"xGOfAx8PSqIUzu1IhmX/Asem5bUsFhCSLJqKU4ftLog0eDoFr7IMVOpL1tID74ypIux/4UNUuh59grz5j1LwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bae4af38319b49877f61d59a779d508addf30820f30f9215545386e96d09e1e","last_reissued_at":"2026-07-05T03:32:41.849429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:32:41.849429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Chao Wang, Chengjie Wu, Dong Li, Hangyu Mao, Jianye Hao, Pingzhong Tang, Xiaotian Hao, Yihuan Mao, Yiming Lu","submitted_at":"2021-11-17T01:36:40Z","abstract_excerpt":"The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment interactions needed to solve the complex \\emph{ObtainDiamond} task with sparse rewards. To address the challenge, in this paper, we present \\textbf{SEIHAI}, a \\textbf{S}ample-\\textbf{e}ff\\textbf{i}cient \\textbf{H}ierarchical \\textbf{AI}, that fully takes advantage of the human demonstrations and the task structure. Specifically, we split the task into several sequentially dependent s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08857","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/2111.08857/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":"2111.08857","created_at":"2026-07-05T03:32:41.849499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.08857v1","created_at":"2026-07-05T03:32:41.849499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08857","created_at":"2026-07-05T03:32:41.849499+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOXEV44DDG2J","created_at":"2026-07-05T03:32:41.849499+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOXEV44DDG2JQ57W","created_at":"2026-07-05T03:32:41.849499+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOXEV44D","created_at":"2026-07-05T03:32:41.849499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.16291","citing_title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOXEV44DDG2JQ57WDVM2O6OVBC","json":"https://pith.science/pith/JOXEV44DDG2JQ57WDVM2O6OVBC.json","graph_json":"https://pith.science/api/pith-number/JOXEV44DDG2JQ57WDVM2O6OVBC/graph.json","events_json":"https://pith.science/api/pith-number/JOXEV44DDG2JQ57WDVM2O6OVBC/events.json","paper":"https://pith.science/paper/JOXEV44D"},"agent_actions":{"view_html":"https://pith.science/pith/JOXEV44DDG2JQ57WDVM2O6OVBC","download_json":"https://pith.science/pith/JOXEV44DDG2JQ57WDVM2O6OVBC.json","view_paper":"https://pith.science/paper/JOXEV44D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.08857&json=true","fetch_graph":"https://pith.science/api/pith-number/JOXEV44DDG2JQ57WDVM2O6OVBC/graph.json","fetch_events":"https://pith.science/api/pith-number/JOXEV44DDG2JQ57WDVM2O6OVBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOXEV44DDG2JQ57WDVM2O6OVBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOXEV44DDG2JQ57WDVM2O6OVBC/action/storage_attestation","attest_author":"https://pith.science/pith/JOXEV44DDG2JQ57WDVM2O6OVBC/action/author_attestation","sign_citation":"https://pith.science/pith/JOXEV44DDG2JQ57WDVM2O6OVBC/action/citation_signature","submit_replication":"https://pith.science/pith/JOXEV44DDG2JQ57WDVM2O6OVBC/action/replication_record"}},"created_at":"2026-07-05T03:32:41.849499+00:00","updated_at":"2026-07-05T03:32:41.849499+00:00"}