{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:A6UHTLQO4HNUUVLOC37HSTXDAI","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":"198a6835bdfe5ba15c838ff22817932834c068d270dc9d6f0c4390b80f247ade","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-30T09:13:39Z","title_canon_sha256":"3910dd5f7a5c97562cacc00bb6b9ec67759f860f2562aaecfa1b788b41d57ec0"},"schema_version":"1.0","source":{"id":"2111.00210","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00210","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00210v2","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00210","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"pith_short_12","alias_value":"A6UHTLQO4HNU","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"pith_short_16","alias_value":"A6UHTLQO4HNUUVLO","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"pith_short_8","alias_value":"A6UHTLQO","created_at":"2026-07-05T03:40:03Z"}],"graph_snapshots":[{"event_id":"sha256:11c642b8f98b0fbc717ef5f5d5784ec8f5368f10f698d9498c4d2c196c5ccdac","target":"graph","created_at":"2026-07-05T03:40:03Z","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/2111.00210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Pieter Abbeel, Shaohuai Liu, Thanard Kurutach, Weirui Ye, Yang Gao","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-30T09:13:39Z","title":"Mastering Atari Games with Limited Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00210","kind":"arxiv","version":2},"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":"sha256:0ae8e0448e715ff6287ed3f7192390ffb0a3935033c223b22f62d03fa08e3c4f","target":"record","created_at":"2026-07-05T03:40:03Z","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":"198a6835bdfe5ba15c838ff22817932834c068d270dc9d6f0c4390b80f247ade","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-30T09:13:39Z","title_canon_sha256":"3910dd5f7a5c97562cacc00bb6b9ec67759f860f2562aaecfa1b788b41d57ec0"},"schema_version":"1.0","source":{"id":"2111.00210","kind":"arxiv","version":2}},"canonical_sha256":"07a879ae0ee1db4a556e16fe794ee3021179770bffb7e8f5f184c0c995b0e97a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07a879ae0ee1db4a556e16fe794ee3021179770bffb7e8f5f184c0c995b0e97a","first_computed_at":"2026-07-05T03:40:03.811149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:03.811149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Bp1hsLgI4XsacAXdO9p0jIOJmVJFRqPsmcDbStNQcA5vC3mUaCfZ9Kql+s7XuscdoATpzlUEWXnBTNa+UVwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:03.811583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.00210","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ae8e0448e715ff6287ed3f7192390ffb0a3935033c223b22f62d03fa08e3c4f","sha256:11c642b8f98b0fbc717ef5f5d5784ec8f5368f10f698d9498c4d2c196c5ccdac"],"state_sha256":"71fc560860eb3fccafd13612f6c52e565ade600f00ac0aeebb3e0afd867d2e81"}