{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3TAMBJEX4LH744O3HEA2W75TAZ","short_pith_number":"pith:3TAMBJEX","schema_version":"1.0","canonical_sha256":"dcc0c0a497e2cffe71db3901ab7fb3066b7be9afd23e18c8850d2b1bd09e650f","source":{"kind":"arxiv","id":"2106.02229","version":4},"attestation_state":"computed","paper":{"title":"Differentiable Architecture Search for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Daiyi Peng, Eugene Brevdo, John D. Co-Reyes, Summer Yue, Xingyou Song, Yingjie Miao","submitted_at":"2021-06-04T03:08:43Z","abstract_excerpt":"In this paper, we investigate the fundamental question: To what extent are gradient-based neural architecture search (NAS) techniques applicable to RL? Using the original DARTS as a convenient baseline, we discover that the discrete architectures found can achieve up to 250% performance compared to manual architecture designs on both discrete and continuous action space environments across off-policy and on-policy RL algorithms, at only 3x more computation time. Furthermore, through numerous ablation studies, we systematically verify that not only does DARTS correctly upweight operations durin"},"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":"2106.02229","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T03:08:43Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"53de1ff881ffb3976eb3aa68ff394d3d312d9f02c14274d0cce47817fb6a9beb","abstract_canon_sha256":"ca2be7e7c3a0b60ed2c2a2113f9aad9f6fdc017dd0ce2311fe6b6c942044fe52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:56.976294Z","signature_b64":"SzHM/x5pmR1scv9EDlCaVNSvTE9BGRcpKHXv08xLIqBbFj3DSW4O9iv/YhLGx9wunUMBjSPN74kR8afvr902Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcc0c0a497e2cffe71db3901ab7fb3066b7be9afd23e18c8850d2b1bd09e650f","last_reissued_at":"2026-07-05T05:15:56.975896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:56.975896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Architecture Search for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Daiyi Peng, Eugene Brevdo, John D. Co-Reyes, Summer Yue, Xingyou Song, Yingjie Miao","submitted_at":"2021-06-04T03:08:43Z","abstract_excerpt":"In this paper, we investigate the fundamental question: To what extent are gradient-based neural architecture search (NAS) techniques applicable to RL? Using the original DARTS as a convenient baseline, we discover that the discrete architectures found can achieve up to 250% performance compared to manual architecture designs on both discrete and continuous action space environments across off-policy and on-policy RL algorithms, at only 3x more computation time. Furthermore, through numerous ablation studies, we systematically verify that not only does DARTS correctly upweight operations durin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02229","kind":"arxiv","version":4},"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/2106.02229/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":"2106.02229","created_at":"2026-07-05T05:15:56.975971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.02229v4","created_at":"2026-07-05T05:15:56.975971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02229","created_at":"2026-07-05T05:15:56.975971+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TAMBJEX4LH7","created_at":"2026-07-05T05:15:56.975971+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TAMBJEX4LH744O3","created_at":"2026-07-05T05:15:56.975971+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TAMBJEX","created_at":"2026-07-05T05:15:56.975971+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/3TAMBJEX4LH744O3HEA2W75TAZ","json":"https://pith.science/pith/3TAMBJEX4LH744O3HEA2W75TAZ.json","graph_json":"https://pith.science/api/pith-number/3TAMBJEX4LH744O3HEA2W75TAZ/graph.json","events_json":"https://pith.science/api/pith-number/3TAMBJEX4LH744O3HEA2W75TAZ/events.json","paper":"https://pith.science/paper/3TAMBJEX"},"agent_actions":{"view_html":"https://pith.science/pith/3TAMBJEX4LH744O3HEA2W75TAZ","download_json":"https://pith.science/pith/3TAMBJEX4LH744O3HEA2W75TAZ.json","view_paper":"https://pith.science/paper/3TAMBJEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.02229&json=true","fetch_graph":"https://pith.science/api/pith-number/3TAMBJEX4LH744O3HEA2W75TAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3TAMBJEX4LH744O3HEA2W75TAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TAMBJEX4LH744O3HEA2W75TAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TAMBJEX4LH744O3HEA2W75TAZ/action/storage_attestation","attest_author":"https://pith.science/pith/3TAMBJEX4LH744O3HEA2W75TAZ/action/author_attestation","sign_citation":"https://pith.science/pith/3TAMBJEX4LH744O3HEA2W75TAZ/action/citation_signature","submit_replication":"https://pith.science/pith/3TAMBJEX4LH744O3HEA2W75TAZ/action/replication_record"}},"created_at":"2026-07-05T05:15:56.975971+00:00","updated_at":"2026-07-05T05:15:56.975971+00:00"}