{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A6UHTLQO4HNUUVLOC37HSTXDAI","short_pith_number":"pith:A6UHTLQO","schema_version":"1.0","canonical_sha256":"07a879ae0ee1db4a556e16fe794ee3021179770bffb7e8f5f184c0c995b0e97a","source":{"kind":"arxiv","id":"2111.00210","version":2},"attestation_state":"computed","paper":{"title":"Mastering Atari Games with Limited Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Pieter Abbeel, Shaohuai Liu, Thanard Kurutach, Weirui Ye, Yang Gao","submitted_at":"2021-10-30T09:13:39Z","abstract_excerpt":"Reinforcement learning has achieved great success in many applications. However, sample efficiency remains a key challenge, with prominent methods requiring millions (or even billions) of environment steps to train. Recently, there has been significant progress in sample efficient image-based RL algorithms; however, consistent human-level performance on the Atari game benchmark remains an elusive goal. We propose a sample efficient model-based visual RL algorithm built on MuZero, which we name EfficientZero. Our method achieves 194.3% mean human performance and 109.0% median performance on the"},"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":"2111.00210","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-30T09:13:39Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"3910dd5f7a5c97562cacc00bb6b9ec67759f860f2562aaecfa1b788b41d57ec0","abstract_canon_sha256":"198a6835bdfe5ba15c838ff22817932834c068d270dc9d6f0c4390b80f247ade"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:03.811583Z","signature_b64":"6Bp1hsLgI4XsacAXdO9p0jIOJmVJFRqPsmcDbStNQcA5vC3mUaCfZ9Kql+s7XuscdoATpzlUEWXnBTNa+UVwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07a879ae0ee1db4a556e16fe794ee3021179770bffb7e8f5f184c0c995b0e97a","last_reissued_at":"2026-07-05T03:40:03.811149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:03.811149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mastering Atari Games with Limited Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Pieter Abbeel, Shaohuai Liu, Thanard Kurutach, Weirui Ye, Yang Gao","submitted_at":"2021-10-30T09:13:39Z","abstract_excerpt":"Reinforcement learning has achieved great success in many applications. However, sample efficiency remains a key challenge, with prominent methods requiring millions (or even billions) of environment steps to train. Recently, there has been significant progress in sample efficient image-based RL algorithms; however, consistent human-level performance on the Atari game benchmark remains an elusive goal. We propose a sample efficient model-based visual RL algorithm built on MuZero, which we name EfficientZero. Our method achieves 194.3% mean human performance and 109.0% median performance on the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00210","kind":"arxiv","version":2},"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/2111.00210/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":"2111.00210","created_at":"2026-07-05T03:40:03.811210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00210v2","created_at":"2026-07-05T03:40:03.811210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00210","created_at":"2026-07-05T03:40:03.811210+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6UHTLQO4HNU","created_at":"2026-07-05T03:40:03.811210+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6UHTLQO4HNUUVLO","created_at":"2026-07-05T03:40:03.811210+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6UHTLQO","created_at":"2026-07-05T03:40:03.811210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.10137","citing_title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01694","citing_title":"Latent State Design for World Models under Sufficiency Constraints","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6UHTLQO4HNUUVLOC37HSTXDAI","json":"https://pith.science/pith/A6UHTLQO4HNUUVLOC37HSTXDAI.json","graph_json":"https://pith.science/api/pith-number/A6UHTLQO4HNUUVLOC37HSTXDAI/graph.json","events_json":"https://pith.science/api/pith-number/A6UHTLQO4HNUUVLOC37HSTXDAI/events.json","paper":"https://pith.science/paper/A6UHTLQO"},"agent_actions":{"view_html":"https://pith.science/pith/A6UHTLQO4HNUUVLOC37HSTXDAI","download_json":"https://pith.science/pith/A6UHTLQO4HNUUVLOC37HSTXDAI.json","view_paper":"https://pith.science/paper/A6UHTLQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00210&json=true","fetch_graph":"https://pith.science/api/pith-number/A6UHTLQO4HNUUVLOC37HSTXDAI/graph.json","fetch_events":"https://pith.science/api/pith-number/A6UHTLQO4HNUUVLOC37HSTXDAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6UHTLQO4HNUUVLOC37HSTXDAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6UHTLQO4HNUUVLOC37HSTXDAI/action/storage_attestation","attest_author":"https://pith.science/pith/A6UHTLQO4HNUUVLOC37HSTXDAI/action/author_attestation","sign_citation":"https://pith.science/pith/A6UHTLQO4HNUUVLOC37HSTXDAI/action/citation_signature","submit_replication":"https://pith.science/pith/A6UHTLQO4HNUUVLOC37HSTXDAI/action/replication_record"}},"created_at":"2026-07-05T03:40:03.811210+00:00","updated_at":"2026-07-05T03:40:03.811210+00:00"}