{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LYK4QYZCUJ4XZCKMC4RWBQWHBS","short_pith_number":"pith:LYK4QYZC","schema_version":"1.0","canonical_sha256":"5e15c86322a2797c894c172360c2c70cab1ef0c44fde6db6bbdedc796bd929b0","source":{"kind":"arxiv","id":"2212.08235","version":1},"attestation_state":"computed","paper":{"title":"A Simple Decentralized Cross-Entropy Method","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Dale Schuurmans, Jun Jin, Jun Luo, Martin Jagersand, Zichen Zhang","submitted_at":"2022-12-16T02:00:55Z","abstract_excerpt":"Cross-Entropy Method (CEM) is commonly used for planning in model-based reinforcement learning (MBRL) where a centralized approach is typically utilized to update the sampling distribution based on only the top-$k$ operation's results on samples. In this paper, we show that such a centralized approach makes CEM vulnerable to local optima, thus impairing its sample efficiency. To tackle this issue, we propose Decentralized CEM (DecentCEM), a simple but effective improvement over classical CEM, by using an ensemble of CEM instances running independently from one another, and each performing a lo"},"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":"2212.08235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-16T02:00:55Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"c132e503c92f64da7c4c01c38e883cc2a260f222a9051eace5653d5190e09a1f","abstract_canon_sha256":"9e105f765861e40d41d7e2cdf9e7a6b2a38c714741c724226e649248bf678f15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:54.265826Z","signature_b64":"yNVHLWCLZNxgVHYdGuKRPU5To1OZaO/FpInE5tXb6OCGPKX/Pe7jg5PmjI1OKin7vYwyjO68C1MtOWtACPfeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e15c86322a2797c894c172360c2c70cab1ef0c44fde6db6bbdedc796bd929b0","last_reissued_at":"2026-07-05T05:25:54.265427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:54.265427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple Decentralized Cross-Entropy Method","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Dale Schuurmans, Jun Jin, Jun Luo, Martin Jagersand, Zichen Zhang","submitted_at":"2022-12-16T02:00:55Z","abstract_excerpt":"Cross-Entropy Method (CEM) is commonly used for planning in model-based reinforcement learning (MBRL) where a centralized approach is typically utilized to update the sampling distribution based on only the top-$k$ operation's results on samples. In this paper, we show that such a centralized approach makes CEM vulnerable to local optima, thus impairing its sample efficiency. To tackle this issue, we propose Decentralized CEM (DecentCEM), a simple but effective improvement over classical CEM, by using an ensemble of CEM instances running independently from one another, and each performing a lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08235","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/2212.08235/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":"2212.08235","created_at":"2026-07-05T05:25:54.265488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08235v1","created_at":"2026-07-05T05:25:54.265488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08235","created_at":"2026-07-05T05:25:54.265488+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYK4QYZCUJ4X","created_at":"2026-07-05T05:25:54.265488+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYK4QYZCUJ4XZCKM","created_at":"2026-07-05T05:25:54.265488+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYK4QYZC","created_at":"2026-07-05T05:25:54.265488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYK4QYZCUJ4XZCKMC4RWBQWHBS","json":"https://pith.science/pith/LYK4QYZCUJ4XZCKMC4RWBQWHBS.json","graph_json":"https://pith.science/api/pith-number/LYK4QYZCUJ4XZCKMC4RWBQWHBS/graph.json","events_json":"https://pith.science/api/pith-number/LYK4QYZCUJ4XZCKMC4RWBQWHBS/events.json","paper":"https://pith.science/paper/LYK4QYZC"},"agent_actions":{"view_html":"https://pith.science/pith/LYK4QYZCUJ4XZCKMC4RWBQWHBS","download_json":"https://pith.science/pith/LYK4QYZCUJ4XZCKMC4RWBQWHBS.json","view_paper":"https://pith.science/paper/LYK4QYZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08235&json=true","fetch_graph":"https://pith.science/api/pith-number/LYK4QYZCUJ4XZCKMC4RWBQWHBS/graph.json","fetch_events":"https://pith.science/api/pith-number/LYK4QYZCUJ4XZCKMC4RWBQWHBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYK4QYZCUJ4XZCKMC4RWBQWHBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYK4QYZCUJ4XZCKMC4RWBQWHBS/action/storage_attestation","attest_author":"https://pith.science/pith/LYK4QYZCUJ4XZCKMC4RWBQWHBS/action/author_attestation","sign_citation":"https://pith.science/pith/LYK4QYZCUJ4XZCKMC4RWBQWHBS/action/citation_signature","submit_replication":"https://pith.science/pith/LYK4QYZCUJ4XZCKMC4RWBQWHBS/action/replication_record"}},"created_at":"2026-07-05T05:25:54.265488+00:00","updated_at":"2026-07-05T05:25:54.265488+00:00"}