{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6BA5FRABY6CRPYJ4SFXNB7CLJL","short_pith_number":"pith:6BA5FRAB","schema_version":"1.0","canonical_sha256":"f041d2c401c78517e13c916ed0fc4b4ad387ce421dcd4a00c58eb1c5b16d4fbd","source":{"kind":"arxiv","id":"1910.12824","version":3},"attestation_state":"computed","paper":{"title":"Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Gregor K\\\"ohler, J\\\"org K.H. Franke, Noor Awad","submitted_at":"2019-10-28T17:33:26Z","abstract_excerpt":"Current Deep Reinforcement Learning algorithms still heavily rely on handcrafted neural network architectures. We propose a novel approach to automatically find strong topologies for continuous control tasks while only adding a minor overhead in terms of interactions in the environment. To achieve this, we combine Neuroevolution techniques with off-policy training and propose a novel architecture mutation operator. Experiments on five continuous control benchmarks show that the proposed Actor-Critic Neuroevolution algorithm often outperforms the strong Actor-Critic baseline and is capable of a"},"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":"1910.12824","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-28T17:33:26Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"39892664017ec2f6e943a4569fc20ef2a0119727835995f3ac1e06ea16ec1d2d","abstract_canon_sha256":"a9e290a86cb9863ab9b5f2d89299e847aff560b1fba2e7741c92308a57db142b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:18.633591Z","signature_b64":"QGEp3dsHxx/MfmB2miczcIRLQToWTxu2rnq+zoQfRx6pM446MA8JaD6qY6mLEL/Hjxt3Ze5jUHVBHwzzNs+jBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f041d2c401c78517e13c916ed0fc4b4ad387ce421dcd4a00c58eb1c5b16d4fbd","last_reissued_at":"2026-07-05T00:44:18.633123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:18.633123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Gregor K\\\"ohler, J\\\"org K.H. Franke, Noor Awad","submitted_at":"2019-10-28T17:33:26Z","abstract_excerpt":"Current Deep Reinforcement Learning algorithms still heavily rely on handcrafted neural network architectures. We propose a novel approach to automatically find strong topologies for continuous control tasks while only adding a minor overhead in terms of interactions in the environment. To achieve this, we combine Neuroevolution techniques with off-policy training and propose a novel architecture mutation operator. Experiments on five continuous control benchmarks show that the proposed Actor-Critic Neuroevolution algorithm often outperforms the strong Actor-Critic baseline and is capable of a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12824","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.12824/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":"1910.12824","created_at":"2026-07-05T00:44:18.633186+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.12824v3","created_at":"2026-07-05T00:44:18.633186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12824","created_at":"2026-07-05T00:44:18.633186+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BA5FRABY6CR","created_at":"2026-07-05T00:44:18.633186+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BA5FRABY6CRPYJ4","created_at":"2026-07-05T00:44:18.633186+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BA5FRAB","created_at":"2026-07-05T00:44:18.633186+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/6BA5FRABY6CRPYJ4SFXNB7CLJL","json":"https://pith.science/pith/6BA5FRABY6CRPYJ4SFXNB7CLJL.json","graph_json":"https://pith.science/api/pith-number/6BA5FRABY6CRPYJ4SFXNB7CLJL/graph.json","events_json":"https://pith.science/api/pith-number/6BA5FRABY6CRPYJ4SFXNB7CLJL/events.json","paper":"https://pith.science/paper/6BA5FRAB"},"agent_actions":{"view_html":"https://pith.science/pith/6BA5FRABY6CRPYJ4SFXNB7CLJL","download_json":"https://pith.science/pith/6BA5FRABY6CRPYJ4SFXNB7CLJL.json","view_paper":"https://pith.science/paper/6BA5FRAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.12824&json=true","fetch_graph":"https://pith.science/api/pith-number/6BA5FRABY6CRPYJ4SFXNB7CLJL/graph.json","fetch_events":"https://pith.science/api/pith-number/6BA5FRABY6CRPYJ4SFXNB7CLJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BA5FRABY6CRPYJ4SFXNB7CLJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BA5FRABY6CRPYJ4SFXNB7CLJL/action/storage_attestation","attest_author":"https://pith.science/pith/6BA5FRABY6CRPYJ4SFXNB7CLJL/action/author_attestation","sign_citation":"https://pith.science/pith/6BA5FRABY6CRPYJ4SFXNB7CLJL/action/citation_signature","submit_replication":"https://pith.science/pith/6BA5FRABY6CRPYJ4SFXNB7CLJL/action/replication_record"}},"created_at":"2026-07-05T00:44:18.633186+00:00","updated_at":"2026-07-05T00:44:18.633186+00:00"}