{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PBHW6S7DXKLES4OLFCE3WQT5RZ","short_pith_number":"pith:PBHW6S7D","schema_version":"1.0","canonical_sha256":"784f6f4be3ba964971cb2889bb427d8e4415089ebf9f2adb5424fb3c8b30a4c8","source":{"kind":"arxiv","id":"1806.01224","version":2},"attestation_state":"computed","paper":{"title":"Challenges in High-dimensional Reinforcement Learning with Evolution Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Nils M\\\"uller, Tobias Glasmachers","submitted_at":"2018-06-04T17:08:23Z","abstract_excerpt":"Evolution Strategies (ESs) have recently become popular for training deep neural networks, in particular on reinforcement learning tasks, a special form of controller design. Compared to classic problems in continuous direct search, deep networks pose extremely high-dimensional optimization problems, with many thousands or even millions of variables. In addition, many control problems give rise to a stochastic fitness function. Considering the relevance of the application, we study the suitability of evolution strategies for high-dimensional, stochastic problems. Our results give insights into"},"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":"1806.01224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-06-04T17:08:23Z","cross_cats_sorted":[],"title_canon_sha256":"6d52ffa8c0a128de76cd9491ac02e78ec57ad0bdfa069c2950e46e14f9bac39a","abstract_canon_sha256":"3d00b1eb784d1f5a8d91ccab21e0ff325b9888386c747be09779a7260226c265"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:56.708641Z","signature_b64":"5CAqvh1tbDWfFM2ZXx3TrVlNSgDxsyg7+ltjuMl26L7zQjf/C8nKPj4+qJu5uyCnYqb877yw68wR4nJT8HKOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"784f6f4be3ba964971cb2889bb427d8e4415089ebf9f2adb5424fb3c8b30a4c8","last_reissued_at":"2026-05-18T00:11:56.707768Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:56.707768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Challenges in High-dimensional Reinforcement Learning with Evolution Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Nils M\\\"uller, Tobias Glasmachers","submitted_at":"2018-06-04T17:08:23Z","abstract_excerpt":"Evolution Strategies (ESs) have recently become popular for training deep neural networks, in particular on reinforcement learning tasks, a special form of controller design. Compared to classic problems in continuous direct search, deep networks pose extremely high-dimensional optimization problems, with many thousands or even millions of variables. In addition, many control problems give rise to a stochastic fitness function. Considering the relevance of the application, we study the suitability of evolution strategies for high-dimensional, stochastic problems. Our results give insights into"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01224","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":""},"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":"1806.01224","created_at":"2026-05-18T00:11:56.707922+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01224v2","created_at":"2026-05-18T00:11:56.707922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01224","created_at":"2026-05-18T00:11:56.707922+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBHW6S7DXKLE","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBHW6S7DXKLES4OL","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBHW6S7D","created_at":"2026-05-18T12:32:43.782077+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/PBHW6S7DXKLES4OLFCE3WQT5RZ","json":"https://pith.science/pith/PBHW6S7DXKLES4OLFCE3WQT5RZ.json","graph_json":"https://pith.science/api/pith-number/PBHW6S7DXKLES4OLFCE3WQT5RZ/graph.json","events_json":"https://pith.science/api/pith-number/PBHW6S7DXKLES4OLFCE3WQT5RZ/events.json","paper":"https://pith.science/paper/PBHW6S7D"},"agent_actions":{"view_html":"https://pith.science/pith/PBHW6S7DXKLES4OLFCE3WQT5RZ","download_json":"https://pith.science/pith/PBHW6S7DXKLES4OLFCE3WQT5RZ.json","view_paper":"https://pith.science/paper/PBHW6S7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01224&json=true","fetch_graph":"https://pith.science/api/pith-number/PBHW6S7DXKLES4OLFCE3WQT5RZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PBHW6S7DXKLES4OLFCE3WQT5RZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBHW6S7DXKLES4OLFCE3WQT5RZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBHW6S7DXKLES4OLFCE3WQT5RZ/action/storage_attestation","attest_author":"https://pith.science/pith/PBHW6S7DXKLES4OLFCE3WQT5RZ/action/author_attestation","sign_citation":"https://pith.science/pith/PBHW6S7DXKLES4OLFCE3WQT5RZ/action/citation_signature","submit_replication":"https://pith.science/pith/PBHW6S7DXKLES4OLFCE3WQT5RZ/action/replication_record"}},"created_at":"2026-05-18T00:11:56.707922+00:00","updated_at":"2026-05-18T00:11:56.707922+00:00"}