{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RJAFU7QO523NU2GYKSAUHUSIGS","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":"976a1b2412b9582ffe972d8aea641eb22a252a1252eff45fc414caf01b727633","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T19:47:55Z","title_canon_sha256":"f8cd15359fec7bad179c74708ec32cfd414042dcb268d10abe9f59cb9ea987a6"},"schema_version":"1.0","source":{"id":"2202.00063","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00063","created_at":"2026-07-05T05:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00063v3","created_at":"2026-07-05T05:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00063","created_at":"2026-07-05T05:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"RJAFU7QO523N","created_at":"2026-07-05T05:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"RJAFU7QO523NU2GY","created_at":"2026-07-05T05:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"RJAFU7QO","created_at":"2026-07-05T05:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:24b0d736506e803ec787427f07be9b80fbd71a3145e334cee9518d8ba757012c","target":"graph","created_at":"2026-07-05T05:05:02Z","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/2202.00063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alekh Agarwal, Masatoshi Uehara, Mengdi Wang, Wen Sun, Xuezhou Zhang, Yuda Song","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T19:47:55Z","title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00063","kind":"arxiv","version":3},"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":"sha256:55dd950b13cbf0f1ae91b026a8cd143074f27cab5c832dea7ac80c84406447dc","target":"record","created_at":"2026-07-05T05:05:02Z","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":"976a1b2412b9582ffe972d8aea641eb22a252a1252eff45fc414caf01b727633","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T19:47:55Z","title_canon_sha256":"f8cd15359fec7bad179c74708ec32cfd414042dcb268d10abe9f59cb9ea987a6"},"schema_version":"1.0","source":{"id":"2202.00063","kind":"arxiv","version":3}},"canonical_sha256":"8a405a7e0eeeb6da68d8548143d248348dc485c331691a5fb83e5f9aa2999daa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a405a7e0eeeb6da68d8548143d248348dc485c331691a5fb83e5f9aa2999daa","first_computed_at":"2026-07-05T05:05:02.775875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:02.775875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yXlEfiCTS7HK2xk30Dw/G5/uSiIoUYIbD5n/JtwO64/aSB8PY/2aTmyLgroQnIgoUCHODyxCmEgHYlPj9lqfBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:02.776296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.00063","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55dd950b13cbf0f1ae91b026a8cd143074f27cab5c832dea7ac80c84406447dc","sha256:24b0d736506e803ec787427f07be9b80fbd71a3145e334cee9518d8ba757012c"],"state_sha256":"086997ffe5b08850f5335bb741dc8901d81f85ed0d638d3bdf93e4bd7842d5e8"}