{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:N5DFXQKJYQ5KXOL4V6YAJTYX2H","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":"654f2371b9aa5a306e2012cf19b81827533665d4ac9a28fecdcceedcabea4dd7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-09T22:04:34Z","title_canon_sha256":"2362e97334103ae241c5e6b5b5757913a4827e178353e5144f371ee2e4dbf2ff"},"schema_version":"1.0","source":{"id":"2110.04652","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04652","created_at":"2026-07-05T03:46:22Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04652v3","created_at":"2026-07-05T03:46:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04652","created_at":"2026-07-05T03:46:22Z"},{"alias_kind":"pith_short_12","alias_value":"N5DFXQKJYQ5K","created_at":"2026-07-05T03:46:22Z"},{"alias_kind":"pith_short_16","alias_value":"N5DFXQKJYQ5KXOL4","created_at":"2026-07-05T03:46:22Z"},{"alias_kind":"pith_short_8","alias_value":"N5DFXQKJ","created_at":"2026-07-05T03:46:22Z"}],"graph_snapshots":[{"event_id":"sha256:b2220086d99d07c62eee590d5c1d78f69e0898d7c653518e530ca0e33942ceb3","target":"graph","created_at":"2026-07-05T03:46:22Z","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/2110.04652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work studies the question of Representation Learning in RL: how can we learn a compact low-dimensional representation such that on top of the representation we can perform RL procedures such as exploration and exploitation, in a sample efficient manner. We focus on the low-rank Markov Decision Processes (MDPs) where the transition dynamics correspond to a low-rank transition matrix. Unlike prior works that assume the representation is known (e.g., linear MDPs), here we need to learn the representation for the low-rank MDP. We study both the online RL and offline RL settings. For the onlin","authors_text":"Masatoshi Uehara, Wen Sun, Xuezhou Zhang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-09T22:04:34Z","title":"Representation Learning for Online and Offline RL in Low-rank MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04652","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":"sha256:02e4b92143820806a590ea42d39116e2099de9ca637f2f89ee46059e545c41b9","target":"record","created_at":"2026-07-05T03:46:22Z","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":"654f2371b9aa5a306e2012cf19b81827533665d4ac9a28fecdcceedcabea4dd7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-09T22:04:34Z","title_canon_sha256":"2362e97334103ae241c5e6b5b5757913a4827e178353e5144f371ee2e4dbf2ff"},"schema_version":"1.0","source":{"id":"2110.04652","kind":"arxiv","version":3}},"canonical_sha256":"6f465bc149c43aabb97cafb004cf17d1d85dd8e98612fbf3eded5404159fdeb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f465bc149c43aabb97cafb004cf17d1d85dd8e98612fbf3eded5404159fdeb3","first_computed_at":"2026-07-05T03:46:22.726299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:22.726299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Pw0zu2sOUQEzEaPpDuHhKblPIt4iH5stqOtLPuLR1JE8I8FGE6ONQelEbA/ElW7Fy5u+X+Zr8MlDUrpu7VUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:22.726811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04652","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02e4b92143820806a590ea42d39116e2099de9ca637f2f89ee46059e545c41b9","sha256:b2220086d99d07c62eee590d5c1d78f69e0898d7c653518e530ca0e33942ceb3"],"state_sha256":"6878e73cdfb84897c39f3d2e18f97a1b925553317b9306fa8df3cb0172b9ee5f"}