{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3TAMBJEX4LH744O3HEA2W75TAZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ca2be7e7c3a0b60ed2c2a2113f9aad9f6fdc017dd0ce2311fe6b6c942044fe52","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T03:08:43Z","title_canon_sha256":"53de1ff881ffb3976eb3aa68ff394d3d312d9f02c14274d0cce47817fb6a9beb"},"schema_version":"1.0","source":{"id":"2106.02229","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02229","created_at":"2026-07-05T05:15:56Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02229v4","created_at":"2026-07-05T05:15:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02229","created_at":"2026-07-05T05:15:56Z"},{"alias_kind":"pith_short_12","alias_value":"3TAMBJEX4LH7","created_at":"2026-07-05T05:15:56Z"},{"alias_kind":"pith_short_16","alias_value":"3TAMBJEX4LH744O3","created_at":"2026-07-05T05:15:56Z"},{"alias_kind":"pith_short_8","alias_value":"3TAMBJEX","created_at":"2026-07-05T05:15:56Z"}],"graph_snapshots":[{"event_id":"sha256:6e164416cabd3f6554539ed8f69e78325f00fd1380741d80a20f418dcc955bcc","target":"graph","created_at":"2026-07-05T05:15:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.02229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aleksandra Faust, Daiyi Peng, Eugene Brevdo, John D. Co-Reyes, Summer Yue, Xingyou Song, Yingjie Miao","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T03:08:43Z","title":"Differentiable Architecture Search for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02229","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:43680f57bded4b1c71cf4390b3395a601e689a8f97d9ef99119404062bc320d9","target":"record","created_at":"2026-07-05T05:15:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ca2be7e7c3a0b60ed2c2a2113f9aad9f6fdc017dd0ce2311fe6b6c942044fe52","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T03:08:43Z","title_canon_sha256":"53de1ff881ffb3976eb3aa68ff394d3d312d9f02c14274d0cce47817fb6a9beb"},"schema_version":"1.0","source":{"id":"2106.02229","kind":"arxiv","version":4}},"canonical_sha256":"dcc0c0a497e2cffe71db3901ab7fb3066b7be9afd23e18c8850d2b1bd09e650f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcc0c0a497e2cffe71db3901ab7fb3066b7be9afd23e18c8850d2b1bd09e650f","first_computed_at":"2026-07-05T05:15:56.975896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:56.975896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SzHM/x5pmR1scv9EDlCaVNSvTE9BGRcpKHXv08xLIqBbFj3DSW4O9iv/YhLGx9wunUMBjSPN74kR8afvr902Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:56.976294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02229","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43680f57bded4b1c71cf4390b3395a601e689a8f97d9ef99119404062bc320d9","sha256:6e164416cabd3f6554539ed8f69e78325f00fd1380741d80a20f418dcc955bcc"],"state_sha256":"7483c7eb4a1be865ddb6c8973441e664b98b4585f04c5f49cec5e4ef3d49a2dc"}