{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:W57HVLN23UGHFDGPK7Y4SZBACV","short_pith_number":"pith:W57HVLN2","schema_version":"1.0","canonical_sha256":"b77e7aadbadd0c728ccf57f1c96420157ddeeeeffc10ff6e254085eae87cd28d","source":{"kind":"arxiv","id":"2008.06389","version":1},"attestation_state":"computed","paper":{"title":"Sample-efficient Cross-Entropy Method for Real-time Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cristina Pinneri, Georg Martius, Jan Achterhold, Joerg Stueckler, Michal Rolinek, Sebastian Blaes, Shambhuraj Sawant","submitted_at":"2020-08-14T14:25:59Z","abstract_excerpt":"Trajectory optimizers for model-based reinforcement learning, such as the Cross-Entropy Method (CEM), can yield compelling results even in high-dimensional control tasks and sparse-reward environments. However, their sampling inefficiency prevents them from being used for real-time planning and control. We propose an improved version of the CEM algorithm for fast planning, with novel additions including temporally-correlated actions and memory, requiring 2.7-22x less samples and yielding a performance increase of 1.2-10x in high-dimensional control problems."},"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":"2008.06389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-14T14:25:59Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"3ce6639616ac6eecad2ed722ed8313cca76e27cc3386324e2384c416b90122d7","abstract_canon_sha256":"17830998e4cd057fee16e7ff203669be2b2fb58ff6a3d6e1774d7f16a96c3e6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:08.971421Z","signature_b64":"uQWa2QiFQYBCP/kkb48nRu5JmTPfwqWtzgXKorRLmCPF0y8ieGzGE58QduqzPsTqvGPANJAT4i3T+e8Mhb/MDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b77e7aadbadd0c728ccf57f1c96420157ddeeeeffc10ff6e254085eae87cd28d","last_reissued_at":"2026-07-05T01:27:08.971057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:08.971057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-efficient Cross-Entropy Method for Real-time Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cristina Pinneri, Georg Martius, Jan Achterhold, Joerg Stueckler, Michal Rolinek, Sebastian Blaes, Shambhuraj Sawant","submitted_at":"2020-08-14T14:25:59Z","abstract_excerpt":"Trajectory optimizers for model-based reinforcement learning, such as the Cross-Entropy Method (CEM), can yield compelling results even in high-dimensional control tasks and sparse-reward environments. However, their sampling inefficiency prevents them from being used for real-time planning and control. We propose an improved version of the CEM algorithm for fast planning, with novel additions including temporally-correlated actions and memory, requiring 2.7-22x less samples and yielding a performance increase of 1.2-10x in high-dimensional control problems."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06389","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/2008.06389/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":"2008.06389","created_at":"2026-07-05T01:27:08.971113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.06389v1","created_at":"2026-07-05T01:27:08.971113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06389","created_at":"2026-07-05T01:27:08.971113+00:00"},{"alias_kind":"pith_short_12","alias_value":"W57HVLN23UGH","created_at":"2026-07-05T01:27:08.971113+00:00"},{"alias_kind":"pith_short_16","alias_value":"W57HVLN23UGHFDGP","created_at":"2026-07-05T01:27:08.971113+00:00"},{"alias_kind":"pith_short_8","alias_value":"W57HVLN2","created_at":"2026-07-05T01:27:08.971113+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/W57HVLN23UGHFDGPK7Y4SZBACV","json":"https://pith.science/pith/W57HVLN23UGHFDGPK7Y4SZBACV.json","graph_json":"https://pith.science/api/pith-number/W57HVLN23UGHFDGPK7Y4SZBACV/graph.json","events_json":"https://pith.science/api/pith-number/W57HVLN23UGHFDGPK7Y4SZBACV/events.json","paper":"https://pith.science/paper/W57HVLN2"},"agent_actions":{"view_html":"https://pith.science/pith/W57HVLN23UGHFDGPK7Y4SZBACV","download_json":"https://pith.science/pith/W57HVLN23UGHFDGPK7Y4SZBACV.json","view_paper":"https://pith.science/paper/W57HVLN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.06389&json=true","fetch_graph":"https://pith.science/api/pith-number/W57HVLN23UGHFDGPK7Y4SZBACV/graph.json","fetch_events":"https://pith.science/api/pith-number/W57HVLN23UGHFDGPK7Y4SZBACV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W57HVLN23UGHFDGPK7Y4SZBACV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W57HVLN23UGHFDGPK7Y4SZBACV/action/storage_attestation","attest_author":"https://pith.science/pith/W57HVLN23UGHFDGPK7Y4SZBACV/action/author_attestation","sign_citation":"https://pith.science/pith/W57HVLN23UGHFDGPK7Y4SZBACV/action/citation_signature","submit_replication":"https://pith.science/pith/W57HVLN23UGHFDGPK7Y4SZBACV/action/replication_record"}},"created_at":"2026-07-05T01:27:08.971113+00:00","updated_at":"2026-07-05T01:27:08.971113+00:00"}