{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:W366BR6FKYXDRWX7ZTRUDFDTY5","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":"c54fc2255373f15c6284964d258b651ac7598910a4344258d06069e0ef7216ed","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T17:16:50Z","title_canon_sha256":"cccfb4c3fcf5bb0550c45c97054ba3d61a7dae9f930cc2747d7e1de283089e5c"},"schema_version":"1.0","source":{"id":"2106.11935","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11935","created_at":"2026-07-05T07:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11935v2","created_at":"2026-07-05T07:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11935","created_at":"2026-07-05T07:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"W366BR6FKYXD","created_at":"2026-07-05T07:44:50Z"},{"alias_kind":"pith_short_16","alias_value":"W366BR6FKYXDRWX7","created_at":"2026-07-05T07:44:50Z"},{"alias_kind":"pith_short_8","alias_value":"W366BR6F","created_at":"2026-07-05T07:44:50Z"}],"graph_snapshots":[{"event_id":"sha256:3061a22ed2849973ffb692c6efab1be69efff8f3c36105509fbcb78b428fcb57","target":"graph","created_at":"2026-07-05T07:44:50Z","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/2106.11935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of deep reinforcement learning (DRL) lies in its ability to learn a representation that is well-suited for the exploration and exploitation task. To understand how the choice of representation can improve the efficiency of reinforcement learning (RL), we study representation selection for a class of low-rank Markov Decision Processes (MDPs) where the transition kernel can be represented in a bilinear form. We propose an efficient algorithm, called ReLEX, for representation learning in both online and offline RL. Specifically, we show that the online version of ReLEX, called ReLEX-U","authors_text":"Amy Zhang, Dongruo Zhou, Jiafan He, Quanquan Gu, Weitong Zhang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T17:16:50Z","title":"Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11935","kind":"arxiv","version":2},"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":"sha256:9e4df7556b587d26c79a9aceb75960aa573587e432194ece57cb6e146e133093","target":"record","created_at":"2026-07-05T07:44:50Z","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":"c54fc2255373f15c6284964d258b651ac7598910a4344258d06069e0ef7216ed","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T17:16:50Z","title_canon_sha256":"cccfb4c3fcf5bb0550c45c97054ba3d61a7dae9f930cc2747d7e1de283089e5c"},"schema_version":"1.0","source":{"id":"2106.11935","kind":"arxiv","version":2}},"canonical_sha256":"b6fde0c7c5562e38daffcce3419473c7484afc38cfe7f52736f61616d840106e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6fde0c7c5562e38daffcce3419473c7484afc38cfe7f52736f61616d840106e","first_computed_at":"2026-07-05T07:44:50.266819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:50.266819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LyZVakHuxwUEWK+kJB1/f7To6VXnGEg/7UsEIaM8ALCD7lyAcMS87fhMhofUy+fiDSMNFQVMOQ618ZdfogHHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:50.267293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.11935","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e4df7556b587d26c79a9aceb75960aa573587e432194ece57cb6e146e133093","sha256:3061a22ed2849973ffb692c6efab1be69efff8f3c36105509fbcb78b428fcb57"],"state_sha256":"50ca584363edf4cba9eed5c851c0f381f7f5187d36e9933492860f088fad51d6"}