{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PXSFFQ4RBGGVXSMGD3PBKB7O44","short_pith_number":"pith:PXSFFQ4R","schema_version":"1.0","canonical_sha256":"7de452c391098d5bc9861ede1507eee734da79c0cbcf9e4c1fe69d99251aeaee","source":{"kind":"arxiv","id":"2112.08451","version":1},"attestation_state":"computed","paper":{"title":"Quantum Algorithms for Reinforcement Learning with a Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Aarthi Sundaram, Ashish Kapoor, Daochen Wang, Martin Roetteler, Robin Kothari","submitted_at":"2021-12-15T19:51:49Z","abstract_excerpt":"Reinforcement learning studies how an agent should interact with an environment to maximize its cumulative reward. A standard way to study this question abstractly is to ask how many samples an agent needs from the environment to learn an optimal policy for a $\\gamma$-discounted Markov decision process (MDP). For such an MDP, we design quantum algorithms that approximate an optimal policy ($\\pi^*$), the optimal value function ($v^*$), and the optimal $Q$-function ($q^*$), assuming the algorithms can access samples from the environment in quantum superposition. This assumption is justified when"},"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":"2112.08451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2021-12-15T19:51:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7db37c43595e6f6b550f420e32696bb1670deba98e6961d3c6f5481ccd0c6535","abstract_canon_sha256":"18e27f76cd2d28308219f3643a0904733c36844079bea4c470590bbf98d2cc5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:42:06.728881Z","signature_b64":"8StC5/Ycw9wq+c8fSuHihlr5fzrDkWj8c5nknf27MGc8I3wb/4d8U0HCtyN83rSwRAAYTsuGguRgsiOX27JEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7de452c391098d5bc9861ede1507eee734da79c0cbcf9e4c1fe69d99251aeaee","last_reissued_at":"2026-07-05T03:42:06.728389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:42:06.728389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantum Algorithms for Reinforcement Learning with a Generative Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Aarthi Sundaram, Ashish Kapoor, Daochen Wang, Martin Roetteler, Robin Kothari","submitted_at":"2021-12-15T19:51:49Z","abstract_excerpt":"Reinforcement learning studies how an agent should interact with an environment to maximize its cumulative reward. A standard way to study this question abstractly is to ask how many samples an agent needs from the environment to learn an optimal policy for a $\\gamma$-discounted Markov decision process (MDP). For such an MDP, we design quantum algorithms that approximate an optimal policy ($\\pi^*$), the optimal value function ($v^*$), and the optimal $Q$-function ($q^*$), assuming the algorithms can access samples from the environment in quantum superposition. This assumption is justified when"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08451","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/2112.08451/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":"2112.08451","created_at":"2026-07-05T03:42:06.728447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08451v1","created_at":"2026-07-05T03:42:06.728447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08451","created_at":"2026-07-05T03:42:06.728447+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXSFFQ4RBGGV","created_at":"2026-07-05T03:42:06.728447+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXSFFQ4RBGGVXSMG","created_at":"2026-07-05T03:42:06.728447+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXSFFQ4R","created_at":"2026-07-05T03:42:06.728447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.18208","citing_title":"Quantum framework for Reinforcement Learning: Integrating Markov decision process, quantum arithmetic, and trajectory search","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44","json":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44.json","graph_json":"https://pith.science/api/pith-number/PXSFFQ4RBGGVXSMGD3PBKB7O44/graph.json","events_json":"https://pith.science/api/pith-number/PXSFFQ4RBGGVXSMGD3PBKB7O44/events.json","paper":"https://pith.science/paper/PXSFFQ4R"},"agent_actions":{"view_html":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44","download_json":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44.json","view_paper":"https://pith.science/paper/PXSFFQ4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08451&json=true","fetch_graph":"https://pith.science/api/pith-number/PXSFFQ4RBGGVXSMGD3PBKB7O44/graph.json","fetch_events":"https://pith.science/api/pith-number/PXSFFQ4RBGGVXSMGD3PBKB7O44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/action/storage_attestation","attest_author":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/action/author_attestation","sign_citation":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/action/citation_signature","submit_replication":"https://pith.science/pith/PXSFFQ4RBGGVXSMGD3PBKB7O44/action/replication_record"}},"created_at":"2026-07-05T03:42:06.728447+00:00","updated_at":"2026-07-05T03:42:06.728447+00:00"}