{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7CUGJLZASQYWUYU3IFFS7DLEVB","short_pith_number":"pith:7CUGJLZA","schema_version":"1.0","canonical_sha256":"f8a864af2094316a629b414b2f8d64a86b3d466fe6475e6b813823f25950e534","source":{"kind":"arxiv","id":"1709.07643","version":2},"attestation_state":"computed","paper":{"title":"OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Giovanni De Magistris, Ryuki Tachibana, Tu-Hoa Pham","submitted_at":"2017-09-22T09:10:10Z","abstract_excerpt":"While deep reinforcement learning techniques have recently produced considerable achievements on many decision-making problems, their use in robotics has largely been limited to simulated worlds or restricted motions, since unconstrained trial-and-error interactions in the real world can have undesirable consequences for the robot or its environment. To overcome such limitations, we propose a novel reinforcement learning architecture, OptLayer, that takes as inputs possibly unsafe actions predicted by a neural network and outputs the closest actions that satisfy chosen constraints. While learn"},"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":"1709.07643","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-09-22T09:10:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"28e0ea5baefe8e88ad6c0bf06a617eee8575bb7a664f330dda43f86f74fb4fb4","abstract_canon_sha256":"af6038f30e7c639d18348c7db1b500c909f047d28f97d11bce2e03c6403385bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:44.536651Z","signature_b64":"tavKh3SZ0Hyltpi9bzMvD/uz/9K9lWY2MozGxzoIiOQ2Ufk1T10OYrx51Aw2E8czNztkkb4joA9zoM16f1UNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8a864af2094316a629b414b2f8d64a86b3d466fe6475e6b813823f25950e534","last_reissued_at":"2026-05-18T00:22:44.536053Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:44.536053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Giovanni De Magistris, Ryuki Tachibana, Tu-Hoa Pham","submitted_at":"2017-09-22T09:10:10Z","abstract_excerpt":"While deep reinforcement learning techniques have recently produced considerable achievements on many decision-making problems, their use in robotics has largely been limited to simulated worlds or restricted motions, since unconstrained trial-and-error interactions in the real world can have undesirable consequences for the robot or its environment. To overcome such limitations, we propose a novel reinforcement learning architecture, OptLayer, that takes as inputs possibly unsafe actions predicted by a neural network and outputs the closest actions that satisfy chosen constraints. While learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.07643","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":"1709.07643","created_at":"2026-05-18T00:22:44.536145+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.07643v2","created_at":"2026-05-18T00:22:44.536145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.07643","created_at":"2026-05-18T00:22:44.536145+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CUGJLZASQYW","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CUGJLZASQYWUYU3","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CUGJLZA","created_at":"2026-05-18T12:31:03.183658+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/7CUGJLZASQYWUYU3IFFS7DLEVB","json":"https://pith.science/pith/7CUGJLZASQYWUYU3IFFS7DLEVB.json","graph_json":"https://pith.science/api/pith-number/7CUGJLZASQYWUYU3IFFS7DLEVB/graph.json","events_json":"https://pith.science/api/pith-number/7CUGJLZASQYWUYU3IFFS7DLEVB/events.json","paper":"https://pith.science/paper/7CUGJLZA"},"agent_actions":{"view_html":"https://pith.science/pith/7CUGJLZASQYWUYU3IFFS7DLEVB","download_json":"https://pith.science/pith/7CUGJLZASQYWUYU3IFFS7DLEVB.json","view_paper":"https://pith.science/paper/7CUGJLZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.07643&json=true","fetch_graph":"https://pith.science/api/pith-number/7CUGJLZASQYWUYU3IFFS7DLEVB/graph.json","fetch_events":"https://pith.science/api/pith-number/7CUGJLZASQYWUYU3IFFS7DLEVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CUGJLZASQYWUYU3IFFS7DLEVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CUGJLZASQYWUYU3IFFS7DLEVB/action/storage_attestation","attest_author":"https://pith.science/pith/7CUGJLZASQYWUYU3IFFS7DLEVB/action/author_attestation","sign_citation":"https://pith.science/pith/7CUGJLZASQYWUYU3IFFS7DLEVB/action/citation_signature","submit_replication":"https://pith.science/pith/7CUGJLZASQYWUYU3IFFS7DLEVB/action/replication_record"}},"created_at":"2026-05-18T00:22:44.536145+00:00","updated_at":"2026-05-18T00:22:44.536145+00:00"}