{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BSF3MQ356547OHMAZQ6HOQKCUV","short_pith_number":"pith:BSF3MQ35","schema_version":"1.0","canonical_sha256":"0c8bb6437df779f71d80cc3c774142a56eb64e6eea8cf15f79f81a711e3d2f32","source":{"kind":"arxiv","id":"2112.11921","version":1},"attestation_state":"computed","paper":{"title":"Variational Quantum Soft Actor-Critic","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"quant-ph","authors_text":"Qingfeng Lan","submitted_at":"2021-12-20T06:31:06Z","abstract_excerpt":"Quantum computing has a superior advantage in tackling specific problems, such as integer factorization and Simon's problem. For more general tasks in machine learning, by applying variational quantum circuits, more and more quantum algorithms have been proposed recently, especially in supervised learning and unsupervised learning. However, little work has been done in reinforcement learning, arguably more important and challenging. Previous work in quantum reinforcement learning mainly focuses on discrete control tasks where the action space is discrete. In this work, we develop a quantum rei"},"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":"2112.11921","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"quant-ph","submitted_at":"2021-12-20T06:31:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"89f5fc736da0f1569ed7f7a9cec0eeab3b0687c37d416338e4994d5b0fbeb7fe","abstract_canon_sha256":"1d95acccda7b6a7d4a172aaefac5aa75e492e3a74ac7548fd72835cb57dc3ab7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:13.280542Z","signature_b64":"07hFVCJLcXs7uXKbn22PxYfZBovG3ADUI0QTriydgxEmPAGKALQ/w4zTaKH14p9EM4DhKRWhivP7aGTV5b1+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c8bb6437df779f71d80cc3c774142a56eb64e6eea8cf15f79f81a711e3d2f32","last_reissued_at":"2026-07-05T03:43:13.280014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:13.280014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Quantum Soft Actor-Critic","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"quant-ph","authors_text":"Qingfeng Lan","submitted_at":"2021-12-20T06:31:06Z","abstract_excerpt":"Quantum computing has a superior advantage in tackling specific problems, such as integer factorization and Simon's problem. For more general tasks in machine learning, by applying variational quantum circuits, more and more quantum algorithms have been proposed recently, especially in supervised learning and unsupervised learning. However, little work has been done in reinforcement learning, arguably more important and challenging. Previous work in quantum reinforcement learning mainly focuses on discrete control tasks where the action space is discrete. In this work, we develop a quantum rei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11921","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/2112.11921/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":"2112.11921","created_at":"2026-07-05T03:43:13.280068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11921v1","created_at":"2026-07-05T03:43:13.280068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11921","created_at":"2026-07-05T03:43:13.280068+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSF3MQ356547","created_at":"2026-07-05T03:43:13.280068+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSF3MQ356547OHMA","created_at":"2026-07-05T03:43:13.280068+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSF3MQ35","created_at":"2026-07-05T03:43:13.280068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30724","citing_title":"Research progress on quantum neural networks and quantum machine learning","ref_index":176,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18208","citing_title":"Quantum framework for Reinforcement Learning: Integrating Markov decision process, quantum arithmetic, and trajectory search","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16002","citing_title":"Scalable Quantum Reinforcement Learning on NISQ Devices with Dynamic-Circuit Qubit Reuse and Grover Optimization","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01716","citing_title":"Towards Real-time Control of a CartPole System on a Quantum Computer","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSF3MQ356547OHMAZQ6HOQKCUV","json":"https://pith.science/pith/BSF3MQ356547OHMAZQ6HOQKCUV.json","graph_json":"https://pith.science/api/pith-number/BSF3MQ356547OHMAZQ6HOQKCUV/graph.json","events_json":"https://pith.science/api/pith-number/BSF3MQ356547OHMAZQ6HOQKCUV/events.json","paper":"https://pith.science/paper/BSF3MQ35"},"agent_actions":{"view_html":"https://pith.science/pith/BSF3MQ356547OHMAZQ6HOQKCUV","download_json":"https://pith.science/pith/BSF3MQ356547OHMAZQ6HOQKCUV.json","view_paper":"https://pith.science/paper/BSF3MQ35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11921&json=true","fetch_graph":"https://pith.science/api/pith-number/BSF3MQ356547OHMAZQ6HOQKCUV/graph.json","fetch_events":"https://pith.science/api/pith-number/BSF3MQ356547OHMAZQ6HOQKCUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSF3MQ356547OHMAZQ6HOQKCUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSF3MQ356547OHMAZQ6HOQKCUV/action/storage_attestation","attest_author":"https://pith.science/pith/BSF3MQ356547OHMAZQ6HOQKCUV/action/author_attestation","sign_citation":"https://pith.science/pith/BSF3MQ356547OHMAZQ6HOQKCUV/action/citation_signature","submit_replication":"https://pith.science/pith/BSF3MQ356547OHMAZQ6HOQKCUV/action/replication_record"}},"created_at":"2026-07-05T03:43:13.280068+00:00","updated_at":"2026-07-05T03:43:13.280068+00:00"}