{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PPLRSA3E6RO3JXJ52EITK4IAJY","short_pith_number":"pith:PPLRSA3E","schema_version":"1.0","canonical_sha256":"7bd7190364f45db4dd3dd1113571004e0b7e18f8e8834d811d95de1ecb52f793","source":{"kind":"arxiv","id":"1802.04063","version":2},"attestation_state":"computed","paper":{"title":"Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["quant-ph"],"primary_cat":"cs.LG","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Moritz August","submitted_at":"2018-02-12T14:27:54Z","abstract_excerpt":"In this work we introduce the application of black-box quantum control as an interesting rein- forcement learning problem to the machine learning community. We analyze the structure of the reinforcement learning problems arising in quantum physics and argue that agents parameterized by long short-term memory (LSTM) networks trained via stochastic policy gradients yield a general method to solving them. In this context we introduce a variant of the proximal policy optimization (PPO) algorithm called the memory proximal policy optimization (MPPO) which is based on this analysis. We then show how"},"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":"1802.04063","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T14:27:54Z","cross_cats_sorted":["quant-ph"],"title_canon_sha256":"c47af10100698f98d235d5228938be57c887efbf6ffc206da016f7c88790d6bf","abstract_canon_sha256":"8d79e542c1431d26e4739ec72a1942ce7f8a39182cf1864de71de8b48eaaa4ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:35.613306Z","signature_b64":"8h9oD9X9KHbPeNA3rTyrNUZ5dPUMpl5UVmCehgoywHHxprzd/Yy3rRCELBPo/iYlUl1pUoLDn1ocWEC6RS+pDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bd7190364f45db4dd3dd1113571004e0b7e18f8e8834d811d95de1ecb52f793","last_reissued_at":"2026-05-18T00:18:35.612567Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:35.612567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["quant-ph"],"primary_cat":"cs.LG","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Moritz August","submitted_at":"2018-02-12T14:27:54Z","abstract_excerpt":"In this work we introduce the application of black-box quantum control as an interesting rein- forcement learning problem to the machine learning community. We analyze the structure of the reinforcement learning problems arising in quantum physics and argue that agents parameterized by long short-term memory (LSTM) networks trained via stochastic policy gradients yield a general method to solving them. In this context we introduce a variant of the proximal policy optimization (PPO) algorithm called the memory proximal policy optimization (MPPO) which is based on this analysis. We then show how"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04063","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":"1802.04063","created_at":"2026-05-18T00:18:35.612686+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04063v2","created_at":"2026-05-18T00:18:35.612686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04063","created_at":"2026-05-18T00:18:35.612686+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPLRSA3E6RO3","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPLRSA3E6RO3JXJ5","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPLRSA3E","created_at":"2026-05-18T12:32:46.962924+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/PPLRSA3E6RO3JXJ52EITK4IAJY","json":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY.json","graph_json":"https://pith.science/api/pith-number/PPLRSA3E6RO3JXJ52EITK4IAJY/graph.json","events_json":"https://pith.science/api/pith-number/PPLRSA3E6RO3JXJ52EITK4IAJY/events.json","paper":"https://pith.science/paper/PPLRSA3E"},"agent_actions":{"view_html":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY","download_json":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY.json","view_paper":"https://pith.science/paper/PPLRSA3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04063&json=true","fetch_graph":"https://pith.science/api/pith-number/PPLRSA3E6RO3JXJ52EITK4IAJY/graph.json","fetch_events":"https://pith.science/api/pith-number/PPLRSA3E6RO3JXJ52EITK4IAJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/action/storage_attestation","attest_author":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/action/author_attestation","sign_citation":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/action/citation_signature","submit_replication":"https://pith.science/pith/PPLRSA3E6RO3JXJ52EITK4IAJY/action/replication_record"}},"created_at":"2026-05-18T00:18:35.612686+00:00","updated_at":"2026-05-18T00:18:35.612686+00:00"}