{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:POFIV2CG6MVQUC5MHX6WMMGNH3","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":"530e0a2030a4a54462d54f6899a4e5b1a15819b09295a07f29693b1f33ce3930","cross_cats_sorted":["cs.AI","math.OC","quant-ph","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T17:24:23Z","title_canon_sha256":"4c1c2075e80b578cd95cb300315e14bb0ca2a129139ac4cfdda515f62a6de7ec"},"schema_version":"1.0","source":{"id":"2507.22854","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22854","created_at":"2026-07-05T11:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22854v2","created_at":"2026-07-05T11:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22854","created_at":"2026-07-05T11:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"POFIV2CG6MVQ","created_at":"2026-07-05T11:51:33Z"},{"alias_kind":"pith_short_16","alias_value":"POFIV2CG6MVQUC5M","created_at":"2026-07-05T11:51:33Z"},{"alias_kind":"pith_short_8","alias_value":"POFIV2CG","created_at":"2026-07-05T11:51:33Z"}],"graph_snapshots":[{"event_id":"sha256:244ba8bddbf14c47de3a4ade8bf56dc39de91fcba70e0bcaa53c5462acfede07","target":"graph","created_at":"2026-07-05T11:51:33Z","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/2507.22854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose novel classical and quantum online algorithms for learning finite-horizon and infinite-horizon average-reward Markov Decision Processes (MDPs). Our algorithms are based on a hybrid exploration-generative reinforcement learning (RL) model wherein the agent can, from time to time, freely interact with the environment in a generative sampling fashion, i.e., by having access to a \"simulator\". By employing known classical and new quantum algorithms for approximating optimal policies under a generative model within our learning algorithms, we show that it is possible to avoid several para","authors_text":"Andris Ambainis, Debbie Lim, Joao F. Doriguello","cross_cats":["cs.AI","math.OC","quant-ph","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T17:24:23Z","title":"A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22854","kind":"arxiv","version":2},"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":"sha256:80cfd5840b7de8c6066778be856dc34476afa522b4f2834fb9761d15e1c6b9b7","target":"record","created_at":"2026-07-05T11:51:33Z","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":"530e0a2030a4a54462d54f6899a4e5b1a15819b09295a07f29693b1f33ce3930","cross_cats_sorted":["cs.AI","math.OC","quant-ph","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T17:24:23Z","title_canon_sha256":"4c1c2075e80b578cd95cb300315e14bb0ca2a129139ac4cfdda515f62a6de7ec"},"schema_version":"1.0","source":{"id":"2507.22854","kind":"arxiv","version":2}},"canonical_sha256":"7b8a8ae846f32b0a0bac3dfd6630cd3ee627d242335bb41b73b49fb005b4ea86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b8a8ae846f32b0a0bac3dfd6630cd3ee627d242335bb41b73b49fb005b4ea86","first_computed_at":"2026-07-05T11:51:33.040899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:33.040899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IRGVFl/br0k5C0CyrC5F/JV/CSAAjj+6FBtA4iwOkVmYLzQfTYTRWrBDgLh1XJemjzCaHz594pH5OBKBkswqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:33.041422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22854","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80cfd5840b7de8c6066778be856dc34476afa522b4f2834fb9761d15e1c6b9b7","sha256:244ba8bddbf14c47de3a4ade8bf56dc39de91fcba70e0bcaa53c5462acfede07"],"state_sha256":"c73975e60e891b98d3daf7d23f7ed4887f1357668bb95a3667bae1d3db4316b4"}