{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:W366BR6FKYXDRWX7ZTRUDFDTY5","short_pith_number":"pith:W366BR6F","schema_version":"1.0","canonical_sha256":"b6fde0c7c5562e38daffcce3419473c7484afc38cfe7f52736f61616d840106e","source":{"kind":"arxiv","id":"2106.11935","version":2},"attestation_state":"computed","paper":{"title":"Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Dongruo Zhou, Jiafan He, Quanquan Gu, Weitong Zhang","submitted_at":"2021-06-22T17:16:50Z","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"},"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":"2106.11935","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T17:16:50Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"cccfb4c3fcf5bb0550c45c97054ba3d61a7dae9f930cc2747d7e1de283089e5c","abstract_canon_sha256":"c54fc2255373f15c6284964d258b651ac7598910a4344258d06069e0ef7216ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:50.267293Z","signature_b64":"LyZVakHuxwUEWK+kJB1/f7To6VXnGEg/7UsEIaM8ALCD7lyAcMS87fhMhofUy+fiDSMNFQVMOQ618ZdfogHHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6fde0c7c5562e38daffcce3419473c7484afc38cfe7f52736f61616d840106e","last_reissued_at":"2026-07-05T07:44:50.266819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:50.266819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Dongruo Zhou, Jiafan He, Quanquan Gu, Weitong Zhang","submitted_at":"2021-06-22T17:16:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11935","kind":"arxiv","version":2},"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/2106.11935/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":"2106.11935","created_at":"2026-07-05T07:44:50.266877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.11935v2","created_at":"2026-07-05T07:44:50.266877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11935","created_at":"2026-07-05T07:44:50.266877+00:00"},{"alias_kind":"pith_short_12","alias_value":"W366BR6FKYXD","created_at":"2026-07-05T07:44:50.266877+00:00"},{"alias_kind":"pith_short_16","alias_value":"W366BR6FKYXDRWX7","created_at":"2026-07-05T07:44:50.266877+00:00"},{"alias_kind":"pith_short_8","alias_value":"W366BR6F","created_at":"2026-07-05T07:44:50.266877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W366BR6FKYXDRWX7ZTRUDFDTY5","json":"https://pith.science/pith/W366BR6FKYXDRWX7ZTRUDFDTY5.json","graph_json":"https://pith.science/api/pith-number/W366BR6FKYXDRWX7ZTRUDFDTY5/graph.json","events_json":"https://pith.science/api/pith-number/W366BR6FKYXDRWX7ZTRUDFDTY5/events.json","paper":"https://pith.science/paper/W366BR6F"},"agent_actions":{"view_html":"https://pith.science/pith/W366BR6FKYXDRWX7ZTRUDFDTY5","download_json":"https://pith.science/pith/W366BR6FKYXDRWX7ZTRUDFDTY5.json","view_paper":"https://pith.science/paper/W366BR6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.11935&json=true","fetch_graph":"https://pith.science/api/pith-number/W366BR6FKYXDRWX7ZTRUDFDTY5/graph.json","fetch_events":"https://pith.science/api/pith-number/W366BR6FKYXDRWX7ZTRUDFDTY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W366BR6FKYXDRWX7ZTRUDFDTY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W366BR6FKYXDRWX7ZTRUDFDTY5/action/storage_attestation","attest_author":"https://pith.science/pith/W366BR6FKYXDRWX7ZTRUDFDTY5/action/author_attestation","sign_citation":"https://pith.science/pith/W366BR6FKYXDRWX7ZTRUDFDTY5/action/citation_signature","submit_replication":"https://pith.science/pith/W366BR6FKYXDRWX7ZTRUDFDTY5/action/replication_record"}},"created_at":"2026-07-05T07:44:50.266877+00:00","updated_at":"2026-07-05T07:44:50.266877+00:00"}