{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GTKLNEPZXJNDTCX2UPAGMA3PUG","short_pith_number":"pith:GTKLNEPZ","schema_version":"1.0","canonical_sha256":"34d4b691f9ba5a398afaa3c066036fa19704fdf865d02acf793381d4d13aa9c1","source":{"kind":"arxiv","id":"2004.12323","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning assisted Quantum Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn"],"primary_cat":"quant-ph","authors_text":"Emanuele Panizon, Giuseppe E. Santoro, Glen B. Mbeng, Matteo M. Wauters","submitted_at":"2020-04-26T09:19:37Z","abstract_excerpt":"We propose a reinforcement learning (RL) scheme for feedback quantum control within the quan-tum approximate optimization algorithm (QAOA). QAOA requires a variational minimization for states constructed by applying a sequence of unitary operators, depending on parameters living ina highly dimensional space. We reformulate such a minimum search as a learning task, where a RL agent chooses the control parameters for the unitaries, given partial information on the system. We show that our RL scheme finds a policy converging to the optimal adiabatic solution for QAOA found by Mbeng et al. arXiv:1"},"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":"2004.12323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2020-04-26T09:19:37Z","cross_cats_sorted":["cond-mat.dis-nn"],"title_canon_sha256":"fec75c6f8db8766915821d4ccaf799af63f4ee1a00045b2b4c1e8893f8583a3d","abstract_canon_sha256":"e42b086d0f6222d546ddd05361feeb840cd537cf26cbc5015746c73829b15462"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:09.155595Z","signature_b64":"8a0p0nU0AnzUgTr7e4H/m/PjSLbOItFhl+2qeWjiphcEG+kqES9LhXfZpgJDCazXSmIIQnJxIjFdSCmAcb8uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34d4b691f9ba5a398afaa3c066036fa19704fdf865d02acf793381d4d13aa9c1","last_reissued_at":"2026-07-05T01:37:09.155191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:09.155191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning assisted Quantum Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn"],"primary_cat":"quant-ph","authors_text":"Emanuele Panizon, Giuseppe E. Santoro, Glen B. Mbeng, Matteo M. Wauters","submitted_at":"2020-04-26T09:19:37Z","abstract_excerpt":"We propose a reinforcement learning (RL) scheme for feedback quantum control within the quan-tum approximate optimization algorithm (QAOA). QAOA requires a variational minimization for states constructed by applying a sequence of unitary operators, depending on parameters living ina highly dimensional space. We reformulate such a minimum search as a learning task, where a RL agent chooses the control parameters for the unitaries, given partial information on the system. We show that our RL scheme finds a policy converging to the optimal adiabatic solution for QAOA found by Mbeng et al. arXiv:1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12323","kind":"arxiv","version":1},"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/2004.12323/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":"2004.12323","created_at":"2026-07-05T01:37:09.155256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.12323v1","created_at":"2026-07-05T01:37:09.155256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12323","created_at":"2026-07-05T01:37:09.155256+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTKLNEPZXJND","created_at":"2026-07-05T01:37:09.155256+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTKLNEPZXJNDTCX2","created_at":"2026-07-05T01:37:09.155256+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTKLNEPZ","created_at":"2026-07-05T01:37:09.155256+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/GTKLNEPZXJNDTCX2UPAGMA3PUG","json":"https://pith.science/pith/GTKLNEPZXJNDTCX2UPAGMA3PUG.json","graph_json":"https://pith.science/api/pith-number/GTKLNEPZXJNDTCX2UPAGMA3PUG/graph.json","events_json":"https://pith.science/api/pith-number/GTKLNEPZXJNDTCX2UPAGMA3PUG/events.json","paper":"https://pith.science/paper/GTKLNEPZ"},"agent_actions":{"view_html":"https://pith.science/pith/GTKLNEPZXJNDTCX2UPAGMA3PUG","download_json":"https://pith.science/pith/GTKLNEPZXJNDTCX2UPAGMA3PUG.json","view_paper":"https://pith.science/paper/GTKLNEPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.12323&json=true","fetch_graph":"https://pith.science/api/pith-number/GTKLNEPZXJNDTCX2UPAGMA3PUG/graph.json","fetch_events":"https://pith.science/api/pith-number/GTKLNEPZXJNDTCX2UPAGMA3PUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTKLNEPZXJNDTCX2UPAGMA3PUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTKLNEPZXJNDTCX2UPAGMA3PUG/action/storage_attestation","attest_author":"https://pith.science/pith/GTKLNEPZXJNDTCX2UPAGMA3PUG/action/author_attestation","sign_citation":"https://pith.science/pith/GTKLNEPZXJNDTCX2UPAGMA3PUG/action/citation_signature","submit_replication":"https://pith.science/pith/GTKLNEPZXJNDTCX2UPAGMA3PUG/action/replication_record"}},"created_at":"2026-07-05T01:37:09.155256+00:00","updated_at":"2026-07-05T01:37:09.155256+00:00"}