{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IOENMXH2LHTLIADTCEXZMYTAEM","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":"27ce080b20428fee45fd02e812eb76098d5bfa4178382f31e58c21eeac3afbb0","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2022-12-19T09:45:58Z","title_canon_sha256":"1fa106b62722ca7b10a05661cd8a9395785a0a19b7f78d577ec1bc609fa1e88e"},"schema_version":"1.0","source":{"id":"2212.09328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09328","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09328v1","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09328","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"pith_short_12","alias_value":"IOENMXH2LHTL","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"pith_short_16","alias_value":"IOENMXH2LHTLIADT","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"pith_short_8","alias_value":"IOENMXH2","created_at":"2026-07-05T06:33:03Z"}],"graph_snapshots":[{"event_id":"sha256:8ca40c04d7a1b708cdc109b871ca9e5ed729c5af17d40404a43dcf09df014a02","target":"graph","created_at":"2026-07-05T06:33:03Z","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/2212.09328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the power and limitations of quantum access to data in machine learning tasks is primordial to assess the potential of quantum computing in artificial intelligence. Previous works have already shown that speed-ups in learning are possible when given quantum access to reinforcement learning environments. Yet, the applicability of quantum algorithms in this setting remains very limited, notably in environments with large state and action spaces. In this work, we design quantum algorithms to train state-of-the-art reinforcement learning policies by exploiting quantum interactions wi","authors_text":"Arjan Cornelissen, M\\=aris Ozols, Sofiene Jerbi, Vedran Dunjko","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2022-12-19T09:45:58Z","title":"Quantum policy gradient algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09328","kind":"arxiv","version":1},"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":"sha256:896805360cdabea2c16341960060afee16cc8e1821292df62780556ecce8e136","target":"record","created_at":"2026-07-05T06:33:03Z","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":"27ce080b20428fee45fd02e812eb76098d5bfa4178382f31e58c21eeac3afbb0","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2022-12-19T09:45:58Z","title_canon_sha256":"1fa106b62722ca7b10a05661cd8a9395785a0a19b7f78d577ec1bc609fa1e88e"},"schema_version":"1.0","source":{"id":"2212.09328","kind":"arxiv","version":1}},"canonical_sha256":"4388d65cfa59e6b40073112f9662602319ac923efb2615a35b0996be35075068","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4388d65cfa59e6b40073112f9662602319ac923efb2615a35b0996be35075068","first_computed_at":"2026-07-05T06:33:03.497521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:03.497521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tKHZEJQhe4ISmUXCznjSQyHpWSmqfa7BjLHpyBx0LHIGVfU59JOsktMeLFUbnQAu6r6yxZfn324bdoCzlwHDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:03.498000Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:896805360cdabea2c16341960060afee16cc8e1821292df62780556ecce8e136","sha256:8ca40c04d7a1b708cdc109b871ca9e5ed729c5af17d40404a43dcf09df014a02"],"state_sha256":"74b654b000e4c2d5c671047aa0b221c10c35845a35c5067fcce69430db8f52d3"}