{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:POFIV2CG6MVQUC5MHX6WMMGNH3","short_pith_number":"pith:POFIV2CG","schema_version":"1.0","canonical_sha256":"7b8a8ae846f32b0a0bac3dfd6630cd3ee627d242335bb41b73b49fb005b4ea86","source":{"kind":"arxiv","id":"2507.22854","version":2},"attestation_state":"computed","paper":{"title":"A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC","quant-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andris Ambainis, Debbie Lim, Joao F. Doriguello","submitted_at":"2025-07-30T17:24:23Z","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"},"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":"2507.22854","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T17:24:23Z","cross_cats_sorted":["cs.AI","math.OC","quant-ph","stat.ML"],"title_canon_sha256":"4c1c2075e80b578cd95cb300315e14bb0ca2a129139ac4cfdda515f62a6de7ec","abstract_canon_sha256":"530e0a2030a4a54462d54f6899a4e5b1a15819b09295a07f29693b1f33ce3930"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:33.041422Z","signature_b64":"IRGVFl/br0k5C0CyrC5F/JV/CSAAjj+6FBtA4iwOkVmYLzQfTYTRWrBDgLh1XJemjzCaHz594pH5OBKBkswqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b8a8ae846f32b0a0bac3dfd6630cd3ee627d242335bb41b73b49fb005b4ea86","last_reissued_at":"2026-07-05T11:51:33.040899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:33.040899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC","quant-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andris Ambainis, Debbie Lim, Joao F. Doriguello","submitted_at":"2025-07-30T17:24:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22854","kind":"arxiv","version":2},"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/2507.22854/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":"2507.22854","created_at":"2026-07-05T11:51:33.040958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22854v2","created_at":"2026-07-05T11:51:33.040958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22854","created_at":"2026-07-05T11:51:33.040958+00:00"},{"alias_kind":"pith_short_12","alias_value":"POFIV2CG6MVQ","created_at":"2026-07-05T11:51:33.040958+00:00"},{"alias_kind":"pith_short_16","alias_value":"POFIV2CG6MVQUC5M","created_at":"2026-07-05T11:51:33.040958+00:00"},{"alias_kind":"pith_short_8","alias_value":"POFIV2CG","created_at":"2026-07-05T11:51:33.040958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POFIV2CG6MVQUC5MHX6WMMGNH3","json":"https://pith.science/pith/POFIV2CG6MVQUC5MHX6WMMGNH3.json","graph_json":"https://pith.science/api/pith-number/POFIV2CG6MVQUC5MHX6WMMGNH3/graph.json","events_json":"https://pith.science/api/pith-number/POFIV2CG6MVQUC5MHX6WMMGNH3/events.json","paper":"https://pith.science/paper/POFIV2CG"},"agent_actions":{"view_html":"https://pith.science/pith/POFIV2CG6MVQUC5MHX6WMMGNH3","download_json":"https://pith.science/pith/POFIV2CG6MVQUC5MHX6WMMGNH3.json","view_paper":"https://pith.science/paper/POFIV2CG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22854&json=true","fetch_graph":"https://pith.science/api/pith-number/POFIV2CG6MVQUC5MHX6WMMGNH3/graph.json","fetch_events":"https://pith.science/api/pith-number/POFIV2CG6MVQUC5MHX6WMMGNH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POFIV2CG6MVQUC5MHX6WMMGNH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POFIV2CG6MVQUC5MHX6WMMGNH3/action/storage_attestation","attest_author":"https://pith.science/pith/POFIV2CG6MVQUC5MHX6WMMGNH3/action/author_attestation","sign_citation":"https://pith.science/pith/POFIV2CG6MVQUC5MHX6WMMGNH3/action/citation_signature","submit_replication":"https://pith.science/pith/POFIV2CG6MVQUC5MHX6WMMGNH3/action/replication_record"}},"created_at":"2026-07-05T11:51:33.040958+00:00","updated_at":"2026-07-05T11:51:33.040958+00:00"}