{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SWZQ2SWAZVZD3X7GFBDH4M4GNG","short_pith_number":"pith:SWZQ2SWA","schema_version":"1.0","canonical_sha256":"95b30d4ac0cd723ddfe628467e338669a81866f3cb0b9986d2758b219e330c9f","source":{"kind":"arxiv","id":"1810.01222","version":3},"attestation_state":"computed","paper":{"title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alo\\\"is Pourchot, Olivier Sigaud","submitted_at":"2018-10-02T13:12:13Z","abstract_excerpt":"Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency. By contrast, the latter is more sample efficient, but the most sample efficient variants are also rather unstable and highly sensitive to hyper-parameter setting. So far, these families of methods have mostly been compared as competing tools. However, an emerging approach consists in combining them so as to get the best of both worlds. Two previously existing combinations use either an ad"},"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":"1810.01222","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T13:12:13Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"f2817c4d5aeba3714f960b02f843e7b31c60722151ed6c6b0abdf541c4737dfd","abstract_canon_sha256":"c81b556503e454e0786d053c258114ff8aa5bdd705b570d330759776bf6d37b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:22.449853Z","signature_b64":"AW1QQhJf705jjwYpCZQDhFgZEHe6OPw9bU8LVuPDkgAJgvE1vuc9Qd6hvi9dAktKS4YfiFvsdH+DIvM+KQv/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95b30d4ac0cd723ddfe628467e338669a81866f3cb0b9986d2758b219e330c9f","last_reissued_at":"2026-05-17T23:54:22.449065Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:22.449065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alo\\\"is Pourchot, Olivier Sigaud","submitted_at":"2018-10-02T13:12:13Z","abstract_excerpt":"Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency. By contrast, the latter is more sample efficient, but the most sample efficient variants are also rather unstable and highly sensitive to hyper-parameter setting. So far, these families of methods have mostly been compared as competing tools. However, an emerging approach consists in combining them so as to get the best of both worlds. Two previously existing combinations use either an ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01222","kind":"arxiv","version":3},"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":"1810.01222","created_at":"2026-05-17T23:54:22.449159+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.01222v3","created_at":"2026-05-17T23:54:22.449159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01222","created_at":"2026-05-17T23:54:22.449159+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWZQ2SWAZVZD","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWZQ2SWAZVZD3X7G","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWZQ2SWA","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.08735","citing_title":"Structure-Conditioned Actor-Critic Branches for Quality-Diversity Reinforcement Learning","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25091","citing_title":"Evolutionary Enhanced Multi-Agent Reinforcement Learning for Cooperative Air Combat","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SWZQ2SWAZVZD3X7GFBDH4M4GNG","json":"https://pith.science/pith/SWZQ2SWAZVZD3X7GFBDH4M4GNG.json","graph_json":"https://pith.science/api/pith-number/SWZQ2SWAZVZD3X7GFBDH4M4GNG/graph.json","events_json":"https://pith.science/api/pith-number/SWZQ2SWAZVZD3X7GFBDH4M4GNG/events.json","paper":"https://pith.science/paper/SWZQ2SWA"},"agent_actions":{"view_html":"https://pith.science/pith/SWZQ2SWAZVZD3X7GFBDH4M4GNG","download_json":"https://pith.science/pith/SWZQ2SWAZVZD3X7GFBDH4M4GNG.json","view_paper":"https://pith.science/paper/SWZQ2SWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.01222&json=true","fetch_graph":"https://pith.science/api/pith-number/SWZQ2SWAZVZD3X7GFBDH4M4GNG/graph.json","fetch_events":"https://pith.science/api/pith-number/SWZQ2SWAZVZD3X7GFBDH4M4GNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWZQ2SWAZVZD3X7GFBDH4M4GNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWZQ2SWAZVZD3X7GFBDH4M4GNG/action/storage_attestation","attest_author":"https://pith.science/pith/SWZQ2SWAZVZD3X7GFBDH4M4GNG/action/author_attestation","sign_citation":"https://pith.science/pith/SWZQ2SWAZVZD3X7GFBDH4M4GNG/action/citation_signature","submit_replication":"https://pith.science/pith/SWZQ2SWAZVZD3X7GFBDH4M4GNG/action/replication_record"}},"created_at":"2026-05-17T23:54:22.449159+00:00","updated_at":"2026-05-17T23:54:22.449159+00:00"}