{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RJAFU7QO523NU2GYKSAUHUSIGS","short_pith_number":"pith:RJAFU7QO","schema_version":"1.0","canonical_sha256":"8a405a7e0eeeb6da68d8548143d248348dc485c331691a5fb83e5f9aa2999daa","source":{"kind":"arxiv","id":"2202.00063","version":3},"attestation_state":"computed","paper":{"title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Masatoshi Uehara, Mengdi Wang, Wen Sun, Xuezhou Zhang, Yuda Song","submitted_at":"2022-01-31T19:47:55Z","abstract_excerpt":"We present BRIEE (Block-structured Representation learning with Interleaved Explore Exploit), an algorithm for efficient reinforcement learning in Markov Decision Processes with block-structured dynamics (i.e., Block MDPs), where rich observations are generated from a set of unknown latent states. BRIEE interleaves latent states discovery, exploration, and exploitation together, and can provably learn a near-optimal policy with sample complexity scaling polynomially in the number of latent states, actions, and the time horizon, with no dependence on the size of the potentially infinite observa"},"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":"2202.00063","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T19:47:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8cd15359fec7bad179c74708ec32cfd414042dcb268d10abe9f59cb9ea987a6","abstract_canon_sha256":"976a1b2412b9582ffe972d8aea641eb22a252a1252eff45fc414caf01b727633"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:02.776296Z","signature_b64":"yXlEfiCTS7HK2xk30Dw/G5/uSiIoUYIbD5n/JtwO64/aSB8PY/2aTmyLgroQnIgoUCHODyxCmEgHYlPj9lqfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a405a7e0eeeb6da68d8548143d248348dc485c331691a5fb83e5f9aa2999daa","last_reissued_at":"2026-07-05T05:05:02.775875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:02.775875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Masatoshi Uehara, Mengdi Wang, Wen Sun, Xuezhou Zhang, Yuda Song","submitted_at":"2022-01-31T19:47:55Z","abstract_excerpt":"We present BRIEE (Block-structured Representation learning with Interleaved Explore Exploit), an algorithm for efficient reinforcement learning in Markov Decision Processes with block-structured dynamics (i.e., Block MDPs), where rich observations are generated from a set of unknown latent states. BRIEE interleaves latent states discovery, exploration, and exploitation together, and can provably learn a near-optimal policy with sample complexity scaling polynomially in the number of latent states, actions, and the time horizon, with no dependence on the size of the potentially infinite observa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00063","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/2202.00063/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":"2202.00063","created_at":"2026-07-05T05:05:02.775933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00063v3","created_at":"2026-07-05T05:05:02.775933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00063","created_at":"2026-07-05T05:05:02.775933+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJAFU7QO523N","created_at":"2026-07-05T05:05:02.775933+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJAFU7QO523NU2GY","created_at":"2026-07-05T05:05:02.775933+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJAFU7QO","created_at":"2026-07-05T05:05:02.775933+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":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJAFU7QO523NU2GYKSAUHUSIGS","json":"https://pith.science/pith/RJAFU7QO523NU2GYKSAUHUSIGS.json","graph_json":"https://pith.science/api/pith-number/RJAFU7QO523NU2GYKSAUHUSIGS/graph.json","events_json":"https://pith.science/api/pith-number/RJAFU7QO523NU2GYKSAUHUSIGS/events.json","paper":"https://pith.science/paper/RJAFU7QO"},"agent_actions":{"view_html":"https://pith.science/pith/RJAFU7QO523NU2GYKSAUHUSIGS","download_json":"https://pith.science/pith/RJAFU7QO523NU2GYKSAUHUSIGS.json","view_paper":"https://pith.science/paper/RJAFU7QO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00063&json=true","fetch_graph":"https://pith.science/api/pith-number/RJAFU7QO523NU2GYKSAUHUSIGS/graph.json","fetch_events":"https://pith.science/api/pith-number/RJAFU7QO523NU2GYKSAUHUSIGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJAFU7QO523NU2GYKSAUHUSIGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJAFU7QO523NU2GYKSAUHUSIGS/action/storage_attestation","attest_author":"https://pith.science/pith/RJAFU7QO523NU2GYKSAUHUSIGS/action/author_attestation","sign_citation":"https://pith.science/pith/RJAFU7QO523NU2GYKSAUHUSIGS/action/citation_signature","submit_replication":"https://pith.science/pith/RJAFU7QO523NU2GYKSAUHUSIGS/action/replication_record"}},"created_at":"2026-07-05T05:05:02.775933+00:00","updated_at":"2026-07-05T05:05:02.775933+00:00"}