{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EBZCE4P4EM7IOLIZ7Z3GSOYI4Q","short_pith_number":"pith:EBZCE4P4","schema_version":"1.0","canonical_sha256":"20722271fc233e872d19fe76693b08e40f7cf0b1cd82088b0f5c81538dbf925e","source":{"kind":"arxiv","id":"2212.11681","version":1},"attestation_state":"computed","paper":{"title":"Variational Quantum Soft Actor-Critic for Robotic Arm Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"quant-ph","authors_text":"Alberto Acuto, Antonio Policicchio, Ludovico Bozzolo, Matteo Conterno, Mattia Pavese, Paola Barill\\`a","submitted_at":"2022-12-20T19:02:24Z","abstract_excerpt":"Deep Reinforcement Learning is emerging as a promising approach for the continuous control task of robotic arm movement. However, the challenges of learning robust and versatile control capabilities are still far from being resolved for real-world applications, mainly because of two common issues of this learning paradigm: the exploration strategy and the slow learning speed, sometimes known as \"the curse of dimensionality\". This work aims at exploring and assessing the advantages of the application of Quantum Computing to one of the state-of-art Reinforcement Learning techniques for continuou"},"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":"2212.11681","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-12-20T19:02:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"502798f4fd36b1fc1a30799b19247213cfcc692ff4d835b93515cddb28e73824","abstract_canon_sha256":"be92669710f7261c44f0b7749e80e9eb90a02bd474d413a6bbd334e0bd0c7232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:41.601650Z","signature_b64":"MWVsHVpOHQ8cGc1APBIvbsXJ9uIYE74z7LtTnR9PCCGPfgYU4gy8o9Pt2LTGlIc5DQc0QQ71pNfZD1XzsQ1dDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20722271fc233e872d19fe76693b08e40f7cf0b1cd82088b0f5c81538dbf925e","last_reissued_at":"2026-07-05T05:27:41.601164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:41.601164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Quantum Soft Actor-Critic for Robotic Arm Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"quant-ph","authors_text":"Alberto Acuto, Antonio Policicchio, Ludovico Bozzolo, Matteo Conterno, Mattia Pavese, Paola Barill\\`a","submitted_at":"2022-12-20T19:02:24Z","abstract_excerpt":"Deep Reinforcement Learning is emerging as a promising approach for the continuous control task of robotic arm movement. However, the challenges of learning robust and versatile control capabilities are still far from being resolved for real-world applications, mainly because of two common issues of this learning paradigm: the exploration strategy and the slow learning speed, sometimes known as \"the curse of dimensionality\". This work aims at exploring and assessing the advantages of the application of Quantum Computing to one of the state-of-art Reinforcement Learning techniques for continuou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11681","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/2212.11681/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":"2212.11681","created_at":"2026-07-05T05:27:41.601221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.11681v1","created_at":"2026-07-05T05:27:41.601221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11681","created_at":"2026-07-05T05:27:41.601221+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBZCE4P4EM7I","created_at":"2026-07-05T05:27:41.601221+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBZCE4P4EM7IOLIZ","created_at":"2026-07-05T05:27:41.601221+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBZCE4P4","created_at":"2026-07-05T05:27:41.601221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10448","citing_title":"Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q","json":"https://pith.science/pith/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q.json","graph_json":"https://pith.science/api/pith-number/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q/graph.json","events_json":"https://pith.science/api/pith-number/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q/events.json","paper":"https://pith.science/paper/EBZCE4P4"},"agent_actions":{"view_html":"https://pith.science/pith/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q","download_json":"https://pith.science/pith/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q.json","view_paper":"https://pith.science/paper/EBZCE4P4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.11681&json=true","fetch_graph":"https://pith.science/api/pith-number/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q/action/storage_attestation","attest_author":"https://pith.science/pith/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q/action/author_attestation","sign_citation":"https://pith.science/pith/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q/action/citation_signature","submit_replication":"https://pith.science/pith/EBZCE4P4EM7IOLIZ7Z3GSOYI4Q/action/replication_record"}},"created_at":"2026-07-05T05:27:41.601221+00:00","updated_at":"2026-07-05T05:27:41.601221+00:00"}