{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OJJKBIC4CA2YKHUHYPLD242YFV","short_pith_number":"pith:OJJKBIC4","schema_version":"1.0","canonical_sha256":"7252a0a05c1035851e87c3d63d73582d7aea465d7a12c79301aa1b29f0322665","source":{"kind":"arxiv","id":"2403.00564","version":2},"attestation_state":"computed","paper":{"title":"EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jiacheng You, Shaohuai Liu, Shengjie Wang, Weirui Ye, Yang Gao","submitted_at":"2024-03-01T14:42:25Z","abstract_excerpt":"Sample efficiency remains a crucial challenge in applying Reinforcement Learning (RL) to real-world tasks. While recent algorithms have made significant strides in improving sample efficiency, none have achieved consistently superior performance across diverse domains. In this paper, we introduce EfficientZero V2, a general framework designed for sample-efficient RL algorithms. We have expanded the performance of EfficientZero to multiple domains, encompassing both continuous and discrete actions, as well as visual and low-dimensional inputs. With a series of improvements we propose, Efficient"},"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":"2403.00564","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T14:42:25Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"3a6aa4984e6bfb8b742a382a71fb2502c329c9e9a886c8939179882301ceb21b","abstract_canon_sha256":"3885076d5d375e70ceebe4afff9d7c4a90a93b53ca1a7e9101f6d875d5c7b65d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:03.358543Z","signature_b64":"/wpQs1qfMJyi55Y7WW+OiNMwdyizEqtvW4lLs8FOCOEdNns8gReXvIh6xNNIV7wpHyLY7jPQ+6SRTQIefKAbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7252a0a05c1035851e87c3d63d73582d7aea465d7a12c79301aa1b29f0322665","last_reissued_at":"2026-07-05T09:06:03.358095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:03.358095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jiacheng You, Shaohuai Liu, Shengjie Wang, Weirui Ye, Yang Gao","submitted_at":"2024-03-01T14:42:25Z","abstract_excerpt":"Sample efficiency remains a crucial challenge in applying Reinforcement Learning (RL) to real-world tasks. While recent algorithms have made significant strides in improving sample efficiency, none have achieved consistently superior performance across diverse domains. In this paper, we introduce EfficientZero V2, a general framework designed for sample-efficient RL algorithms. We have expanded the performance of EfficientZero to multiple domains, encompassing both continuous and discrete actions, as well as visual and low-dimensional inputs. With a series of improvements we propose, Efficient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00564","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/2403.00564/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":"2403.00564","created_at":"2026-07-05T09:06:03.358152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00564v2","created_at":"2026-07-05T09:06:03.358152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00564","created_at":"2026-07-05T09:06:03.358152+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJJKBIC4CA2Y","created_at":"2026-07-05T09:06:03.358152+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJJKBIC4CA2YKHUH","created_at":"2026-07-05T09:06:03.358152+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJJKBIC4","created_at":"2026-07-05T09:06:03.358152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.02635","citing_title":"Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2509.26627","citing_title":"TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07083","citing_title":"Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08019","citing_title":"Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OJJKBIC4CA2YKHUHYPLD242YFV","json":"https://pith.science/pith/OJJKBIC4CA2YKHUHYPLD242YFV.json","graph_json":"https://pith.science/api/pith-number/OJJKBIC4CA2YKHUHYPLD242YFV/graph.json","events_json":"https://pith.science/api/pith-number/OJJKBIC4CA2YKHUHYPLD242YFV/events.json","paper":"https://pith.science/paper/OJJKBIC4"},"agent_actions":{"view_html":"https://pith.science/pith/OJJKBIC4CA2YKHUHYPLD242YFV","download_json":"https://pith.science/pith/OJJKBIC4CA2YKHUHYPLD242YFV.json","view_paper":"https://pith.science/paper/OJJKBIC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00564&json=true","fetch_graph":"https://pith.science/api/pith-number/OJJKBIC4CA2YKHUHYPLD242YFV/graph.json","fetch_events":"https://pith.science/api/pith-number/OJJKBIC4CA2YKHUHYPLD242YFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJJKBIC4CA2YKHUHYPLD242YFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJJKBIC4CA2YKHUHYPLD242YFV/action/storage_attestation","attest_author":"https://pith.science/pith/OJJKBIC4CA2YKHUHYPLD242YFV/action/author_attestation","sign_citation":"https://pith.science/pith/OJJKBIC4CA2YKHUHYPLD242YFV/action/citation_signature","submit_replication":"https://pith.science/pith/OJJKBIC4CA2YKHUHYPLD242YFV/action/replication_record"}},"created_at":"2026-07-05T09:06:03.358152+00:00","updated_at":"2026-07-05T09:06:03.358152+00:00"}