{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GSFPL4OAAR63BZWQZY3IKCL54J","short_pith_number":"pith:GSFPL4OA","schema_version":"1.0","canonical_sha256":"348af5f1c0047db0e6d0ce3685097de2774c92f13d931d3c6496eeb330bfab0d","source":{"kind":"arxiv","id":"1808.05832","version":1},"attestation_state":"computed","paper":{"title":"Importance mixing: Improving sample reuse in evolutionary policy search methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alo\\\"is Pourchot, Nicolas Perrin, Olivier Sigaud","submitted_at":"2018-08-17T11:25:19Z","abstract_excerpt":"Deep neuroevolution, that is evolutionary policy search methods based on deep neural networks, have recently emerged as a competitor to deep reinforcement learning algorithms due to their better parallelization capabilities. However, these methods still suffer from a far worse sample efficiency. In this paper we investigate whether a mechanism known as \"importance mixing\" can significantly improve their sample efficiency. We provide a didactic presentation of importance mixing and we explain how it can be extended to reuse more samples. Then, from an empirical comparison based on a simple benc"},"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":"1808.05832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-17T11:25:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1374c3fada40d03527315792400ecc5973b5b62c690901e8f40c0efbe6a0fd5d","abstract_canon_sha256":"b091e3510c9522e25d5545160ef2e0872950a63544a467ef163730c2be05883b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:51.982485Z","signature_b64":"/0JJjV2CqkaZiTy8EEwzmpADhMI2BEhVvJcmx9XvyfC1qpKT5KwSq0XZNdEAVB2V7UVtRCb1uplJMVzpiAD7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"348af5f1c0047db0e6d0ce3685097de2774c92f13d931d3c6496eeb330bfab0d","last_reissued_at":"2026-05-18T00:07:51.981690Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:51.981690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Importance mixing: Improving sample reuse in evolutionary policy search methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alo\\\"is Pourchot, Nicolas Perrin, Olivier Sigaud","submitted_at":"2018-08-17T11:25:19Z","abstract_excerpt":"Deep neuroevolution, that is evolutionary policy search methods based on deep neural networks, have recently emerged as a competitor to deep reinforcement learning algorithms due to their better parallelization capabilities. However, these methods still suffer from a far worse sample efficiency. In this paper we investigate whether a mechanism known as \"importance mixing\" can significantly improve their sample efficiency. We provide a didactic presentation of importance mixing and we explain how it can be extended to reuse more samples. Then, from an empirical comparison based on a simple benc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05832","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":""},"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":"1808.05832","created_at":"2026-05-18T00:07:51.981816+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.05832v1","created_at":"2026-05-18T00:07:51.981816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05832","created_at":"2026-05-18T00:07:51.981816+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSFPL4OAAR63","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSFPL4OAAR63BZWQ","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSFPL4OA","created_at":"2026-05-18T12:32:25.280505+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/GSFPL4OAAR63BZWQZY3IKCL54J","json":"https://pith.science/pith/GSFPL4OAAR63BZWQZY3IKCL54J.json","graph_json":"https://pith.science/api/pith-number/GSFPL4OAAR63BZWQZY3IKCL54J/graph.json","events_json":"https://pith.science/api/pith-number/GSFPL4OAAR63BZWQZY3IKCL54J/events.json","paper":"https://pith.science/paper/GSFPL4OA"},"agent_actions":{"view_html":"https://pith.science/pith/GSFPL4OAAR63BZWQZY3IKCL54J","download_json":"https://pith.science/pith/GSFPL4OAAR63BZWQZY3IKCL54J.json","view_paper":"https://pith.science/paper/GSFPL4OA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.05832&json=true","fetch_graph":"https://pith.science/api/pith-number/GSFPL4OAAR63BZWQZY3IKCL54J/graph.json","fetch_events":"https://pith.science/api/pith-number/GSFPL4OAAR63BZWQZY3IKCL54J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSFPL4OAAR63BZWQZY3IKCL54J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSFPL4OAAR63BZWQZY3IKCL54J/action/storage_attestation","attest_author":"https://pith.science/pith/GSFPL4OAAR63BZWQZY3IKCL54J/action/author_attestation","sign_citation":"https://pith.science/pith/GSFPL4OAAR63BZWQZY3IKCL54J/action/citation_signature","submit_replication":"https://pith.science/pith/GSFPL4OAAR63BZWQZY3IKCL54J/action/replication_record"}},"created_at":"2026-05-18T00:07:51.981816+00:00","updated_at":"2026-05-18T00:07:51.981816+00:00"}