{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WQ4FZLMHZXO7LAIG6ACJ5Y7TTY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e4149fc409b5cc90f987f839f9db8d45542e4669c264a0027db463a269484bd6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-01-27T17:38:30Z","title_canon_sha256":"5d7e6f60d46ee2680a7d4e1cf9fd0eed36f6f4a2d119256a80ba4005729bea6b"},"schema_version":"1.0","source":{"id":"2501.16243","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16243","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16243v3","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16243","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"pith_short_12","alias_value":"WQ4FZLMHZXO7","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"pith_short_16","alias_value":"WQ4FZLMHZXO7LAIG","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"pith_short_8","alias_value":"WQ4FZLMH","created_at":"2026-07-05T11:29:54Z"}],"graph_snapshots":[{"event_id":"sha256:7994628639c681059cfaf37a842cafb28c09ff0e98732b24c5fa52386eb8a1b0","target":"graph","created_at":"2026-07-05T11:29:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.16243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of quantum reinforcement learning (QRL) under model-free settings with quantum oracle access to the Markov Decision Process (MDP). This paper introduces a Quantum Natural Policy Gradient (QNPG) algorithm, which replaces the random sampling used in classical Natural Policy Gradient (NPG) estimators with a deterministic gradient estimation approach, enabling seamless integration into quantum systems. While this modification introduces a bounded bias in the estimator, the bias decays exponentially with increasing truncation levels. This paper demonstrates that the proposed ","authors_text":"Vaneet Aggarwal, Yang Xu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-01-27T17:38:30Z","title":"Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16243","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:38689a5f75d9888bb6630c7e7e65f4ef8e18e47df89bef233568f81046514e26","target":"record","created_at":"2026-07-05T11:29:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e4149fc409b5cc90f987f839f9db8d45542e4669c264a0027db463a269484bd6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-01-27T17:38:30Z","title_canon_sha256":"5d7e6f60d46ee2680a7d4e1cf9fd0eed36f6f4a2d119256a80ba4005729bea6b"},"schema_version":"1.0","source":{"id":"2501.16243","kind":"arxiv","version":3}},"canonical_sha256":"b4385cad87cdddf58106f0049ee3f39e1dfa55e9924a59b4c18cb3b21d81e469","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4385cad87cdddf58106f0049ee3f39e1dfa55e9924a59b4c18cb3b21d81e469","first_computed_at":"2026-07-05T11:29:54.596593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:54.596593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PvyRhEeE/t5MCNv+8HoR615A0FEpWNKaGnojUS7QUStabKHyMuXZE6VbnB1S4mKbwIUv33y98jum7KC2ZE+rDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:54.596975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16243","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38689a5f75d9888bb6630c7e7e65f4ef8e18e47df89bef233568f81046514e26","sha256:7994628639c681059cfaf37a842cafb28c09ff0e98732b24c5fa52386eb8a1b0"],"state_sha256":"426488ee24d85a0fab95a64a38bfa8ef97f7f0aa75dd600339810878186fd898"}