{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GKJ3GOISPNAS6TC6PP3GZJ6KLH","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":"5722e2184ad4425c3644f595f802748d9eb58ac0932d458f1ba918db49798763","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-10T16:50:40Z","title_canon_sha256":"b780be6893245b98daecdcab62ac0145ac70461a53619644415f17e6be98b38a"},"schema_version":"1.0","source":{"id":"2302.05372","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05372","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05372v3","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05372","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"pith_short_12","alias_value":"GKJ3GOISPNAS","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"pith_short_16","alias_value":"GKJ3GOISPNAS6TC6","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"pith_short_8","alias_value":"GKJ3GOIS","created_at":"2026-07-05T08:28:00Z"}],"graph_snapshots":[{"event_id":"sha256:ea9a48a2e7ad7c59c209a11c29cd39e5af1700fedad068a893226b0080de70d9","target":"graph","created_at":"2026-07-05T08:28:00Z","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/2302.05372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the sample complexity of obtaining an $\\epsilon$-optimal policy in \\emph{Robust} discounted Markov Decision Processes (RMDPs), given only access to a generative model of the nominal kernel. This problem is widely studied in the non-robust case, and it is known that any planning approach applied to an empirical MDP estimated with $\\tilde{\\mathcal{O}}(\\frac{H^3 \\mid S \\mid\\mid A \\mid}{\\epsilon^2})$ samples provides an $\\epsilon$-optimal policy, which is minimax optimal. Results in the robust case are much more scarce. For $sa$- (resp $s$-)rectangular uncertainty sets, the best known sam","authors_text":"Erwan Le Pennec, Matthieu Geist, Pierre Clavier","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-10T16:50:40Z","title":"Towards Minimax Optimality of Model-based Robust Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05372","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:ce50f854fa8642c5afbeaf950b87bf86220b5217f978d2e5fbaabc4c9f87e93b","target":"record","created_at":"2026-07-05T08:28:00Z","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":"5722e2184ad4425c3644f595f802748d9eb58ac0932d458f1ba918db49798763","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-10T16:50:40Z","title_canon_sha256":"b780be6893245b98daecdcab62ac0145ac70461a53619644415f17e6be98b38a"},"schema_version":"1.0","source":{"id":"2302.05372","kind":"arxiv","version":3}},"canonical_sha256":"3293b339127b412f4c5e7bf66ca7ca59f7c043e8b8993004ab5d8e276c90ecd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3293b339127b412f4c5e7bf66ca7ca59f7c043e8b8993004ab5d8e276c90ecd4","first_computed_at":"2026-07-05T08:28:00.186398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:00.186398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DnjUmoa7l73rOElXqFpn24g7pvJ3BBGynjMeLvdGsbA2tmQkRGO6lbiHH8pHp7wRHUaT1MyjwyA8SOL5Omu0DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:00.186795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05372","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce50f854fa8642c5afbeaf950b87bf86220b5217f978d2e5fbaabc4c9f87e93b","sha256:ea9a48a2e7ad7c59c209a11c29cd39e5af1700fedad068a893226b0080de70d9"],"state_sha256":"e6a1ade87ce868868fd27d8ced472415b4023d893a84977d0bb8d91ff9a1814c"}