{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PYV2XK5YMDQTWBJY6HYIUUGOUB","short_pith_number":"pith:PYV2XK5Y","schema_version":"1.0","canonical_sha256":"7e2bababb860e13b0538f1f08a50cea04da5c81c1ac5df1bd88d2b8dda2fe02e","source":{"kind":"arxiv","id":"2207.05738","version":3},"attestation_state":"computed","paper":{"title":"PAC Reinforcement Learning for Predictive State Representations","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Masatoshi Uehara, Wenhao Zhan, Wen Sun","submitted_at":"2022-07-12T17:57:17Z","abstract_excerpt":"In this paper we study online Reinforcement Learning (RL) in partially observable dynamical systems. We focus on the Predictive State Representations (PSRs) model, which is an expressive model that captures other well-known models such as Partially Observable Markov Decision Processes (POMDP). PSR represents the states using a set of predictions of future observations and is defined entirely using observable quantities. We develop a novel model-based algorithm for PSRs that can learn a near optimal policy in sample complexity scaling polynomially with respect to all the relevant parameters of "},"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":"2207.05738","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T17:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"4a534302888de0b2824d81fc1fdf40df322ff8071be0bfdd78a9cd3381993cb2","abstract_canon_sha256":"62d09fdd53c1731bc9b050b0930fc4dd775eec6508201edc61705bc2104bc7cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:14.861432Z","signature_b64":"zBvIjxh5EpZDamNua8NkzNmd5c9pQ1xroI99Ybx2UczxF5OJF4WTN70XKnnszzT/ShXf3VdHOAB2jekQyvGVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e2bababb860e13b0538f1f08a50cea04da5c81c1ac5df1bd88d2b8dda2fe02e","last_reissued_at":"2026-07-05T04:48:14.860922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:14.860922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAC Reinforcement Learning for Predictive State Representations","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Masatoshi Uehara, Wenhao Zhan, Wen Sun","submitted_at":"2022-07-12T17:57:17Z","abstract_excerpt":"In this paper we study online Reinforcement Learning (RL) in partially observable dynamical systems. We focus on the Predictive State Representations (PSRs) model, which is an expressive model that captures other well-known models such as Partially Observable Markov Decision Processes (POMDP). PSR represents the states using a set of predictions of future observations and is defined entirely using observable quantities. We develop a novel model-based algorithm for PSRs that can learn a near optimal policy in sample complexity scaling polynomially with respect to all the relevant parameters of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05738","kind":"arxiv","version":3},"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/2207.05738/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":"2207.05738","created_at":"2026-07-05T04:48:14.860987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05738v3","created_at":"2026-07-05T04:48:14.860987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05738","created_at":"2026-07-05T04:48:14.860987+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYV2XK5YMDQT","created_at":"2026-07-05T04:48:14.860987+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYV2XK5YMDQTWBJY","created_at":"2026-07-05T04:48:14.860987+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYV2XK5Y","created_at":"2026-07-05T04:48:14.860987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01242","citing_title":"Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB","json":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB.json","graph_json":"https://pith.science/api/pith-number/PYV2XK5YMDQTWBJY6HYIUUGOUB/graph.json","events_json":"https://pith.science/api/pith-number/PYV2XK5YMDQTWBJY6HYIUUGOUB/events.json","paper":"https://pith.science/paper/PYV2XK5Y"},"agent_actions":{"view_html":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB","download_json":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB.json","view_paper":"https://pith.science/paper/PYV2XK5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05738&json=true","fetch_graph":"https://pith.science/api/pith-number/PYV2XK5YMDQTWBJY6HYIUUGOUB/graph.json","fetch_events":"https://pith.science/api/pith-number/PYV2XK5YMDQTWBJY6HYIUUGOUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/action/storage_attestation","attest_author":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/action/author_attestation","sign_citation":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/action/citation_signature","submit_replication":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/action/replication_record"}},"created_at":"2026-07-05T04:48:14.860987+00:00","updated_at":"2026-07-05T04:48:14.860987+00:00"}