{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CKYTFZU3DCT2RZVGIMF5G2FULK","short_pith_number":"pith:CKYTFZU3","schema_version":"1.0","canonical_sha256":"12b132e69b18a7a8e6a6430bd368b45aad88558620ab3ffd130bb38fc3af911c","source":{"kind":"arxiv","id":"2101.11071","version":1},"attestation_state":"computed","paper":{"title":"The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Avinash Ummadisingu, Brandon Houghton, Crissman Loomis, John Schulman, Keisuke Nakata, Mario Ynocente Castro, Nicholay Topin, Noboru Sean Kuno, Oriol Vinyals, Ruslan Salakhutdinov, Sam Devlin, Sharada Mohanty, Shinya Shiroshita, Stephanie Milani, William H. Guss","submitted_at":"2021-01-26T20:32:30Z","abstract_excerpt":"Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples, affording only a shrinking segment of the AI community access to their development. Resolution of these limitations requires new, sample-efficient methods. To facilitate research in this direction, we propose this second iteration of the MineRL Competition. The primary goal of the competition is to foster the development of algorithms which can efficiently leverage human demonstrations to drastically reduce the number of samples needed to "},"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":"2101.11071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-26T20:32:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1f6fb941a18fe40c52e306af2f9edda1fba7361774e81e58119955e398ce3d0f","abstract_canon_sha256":"24bd6daae69e8778abdb36b8651f25f1b61533926438aecdfa916bcc47cfe97c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:08.675387Z","signature_b64":"pntN88+lNUlrCpix58b0pGR1ZKVeDCVoZ4B3LGgKwO63i4Wz0tJgDcoxipdKAqhBArmX4AMksXZMHBldK3oDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12b132e69b18a7a8e6a6430bd368b45aad88558620ab3ffd130bb38fc3af911c","last_reissued_at":"2026-07-05T02:10:08.674917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:08.674917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Avinash Ummadisingu, Brandon Houghton, Crissman Loomis, John Schulman, Keisuke Nakata, Mario Ynocente Castro, Nicholay Topin, Noboru Sean Kuno, Oriol Vinyals, Ruslan Salakhutdinov, Sam Devlin, Sharada Mohanty, Shinya Shiroshita, Stephanie Milani, William H. Guss","submitted_at":"2021-01-26T20:32:30Z","abstract_excerpt":"Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples, affording only a shrinking segment of the AI community access to their development. Resolution of these limitations requires new, sample-efficient methods. To facilitate research in this direction, we propose this second iteration of the MineRL Competition. The primary goal of the competition is to foster the development of algorithms which can efficiently leverage human demonstrations to drastically reduce the number of samples needed to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11071","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/2101.11071/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":"2101.11071","created_at":"2026-07-05T02:10:08.674976+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.11071v1","created_at":"2026-07-05T02:10:08.674976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11071","created_at":"2026-07-05T02:10:08.674976+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKYTFZU3DCT2","created_at":"2026-07-05T02:10:08.674976+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKYTFZU3DCT2RZVG","created_at":"2026-07-05T02:10:08.674976+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKYTFZU3","created_at":"2026-07-05T02:10:08.674976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01131","citing_title":"Forager: a lightweight testbed for continual learning with partial observability in RL","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2305.16291","citing_title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKYTFZU3DCT2RZVGIMF5G2FULK","json":"https://pith.science/pith/CKYTFZU3DCT2RZVGIMF5G2FULK.json","graph_json":"https://pith.science/api/pith-number/CKYTFZU3DCT2RZVGIMF5G2FULK/graph.json","events_json":"https://pith.science/api/pith-number/CKYTFZU3DCT2RZVGIMF5G2FULK/events.json","paper":"https://pith.science/paper/CKYTFZU3"},"agent_actions":{"view_html":"https://pith.science/pith/CKYTFZU3DCT2RZVGIMF5G2FULK","download_json":"https://pith.science/pith/CKYTFZU3DCT2RZVGIMF5G2FULK.json","view_paper":"https://pith.science/paper/CKYTFZU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.11071&json=true","fetch_graph":"https://pith.science/api/pith-number/CKYTFZU3DCT2RZVGIMF5G2FULK/graph.json","fetch_events":"https://pith.science/api/pith-number/CKYTFZU3DCT2RZVGIMF5G2FULK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKYTFZU3DCT2RZVGIMF5G2FULK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKYTFZU3DCT2RZVGIMF5G2FULK/action/storage_attestation","attest_author":"https://pith.science/pith/CKYTFZU3DCT2RZVGIMF5G2FULK/action/author_attestation","sign_citation":"https://pith.science/pith/CKYTFZU3DCT2RZVGIMF5G2FULK/action/citation_signature","submit_replication":"https://pith.science/pith/CKYTFZU3DCT2RZVGIMF5G2FULK/action/replication_record"}},"created_at":"2026-07-05T02:10:08.674976+00:00","updated_at":"2026-07-05T02:10:08.674976+00:00"}