{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LECFQ2MHN37LLA2NMSM6ADHS2B","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":"fbb94cba0dc9caf630c22f5d2f913a37c78bd07947c33bbcaa2f02899bbd59d4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T05:18:20Z","title_canon_sha256":"4b0ba21f3ef5d1d7c01437c68755e618de73cf227ce3c04a130f248b543a1e65"},"schema_version":"1.0","source":{"id":"2209.13841","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.13841","created_at":"2026-07-05T05:01:44Z"},{"alias_kind":"arxiv_version","alias_value":"2209.13841v1","created_at":"2026-07-05T05:01:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13841","created_at":"2026-07-05T05:01:44Z"},{"alias_kind":"pith_short_12","alias_value":"LECFQ2MHN37L","created_at":"2026-07-05T05:01:44Z"},{"alias_kind":"pith_short_16","alias_value":"LECFQ2MHN37LLA2N","created_at":"2026-07-05T05:01:44Z"},{"alias_kind":"pith_short_8","alias_value":"LECFQ2MH","created_at":"2026-07-05T05:01:44Z"}],"graph_snapshots":[{"event_id":"sha256:098b21f9d508b9a04fc4a3aa6f3e55e9325e815cb012bd492e8be2b0061d23d2","target":"graph","created_at":"2026-07-05T05:01:44Z","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/2209.13841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has exceeded human performance in many synthetic settings such as video games and Go. However, real-world deployment of end-to-end RL models is less common, as RL models can be very sensitive to slight perturbation of the environment. The robust Markov decision process (MDP) framework -- in which the transition probabilities belong to an uncertainty set around a nominal model -- provides one way to develop robust models. While previous analysis shows RL algorithms are effective assuming access to a generative model, it remains unclear whether RL can be efficient und","authors_text":"Baoxiang Wang, Jing Dong, Jingwei Li, Jingzhao Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T05:18:20Z","title":"Online Policy Optimization for Robust MDP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13841","kind":"arxiv","version":1},"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:bea437e0c4f1c41bf8ff5e9f1d3d34c0e5b34e9a83ecd932bfd683772fea745f","target":"record","created_at":"2026-07-05T05:01:44Z","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":"fbb94cba0dc9caf630c22f5d2f913a37c78bd07947c33bbcaa2f02899bbd59d4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T05:18:20Z","title_canon_sha256":"4b0ba21f3ef5d1d7c01437c68755e618de73cf227ce3c04a130f248b543a1e65"},"schema_version":"1.0","source":{"id":"2209.13841","kind":"arxiv","version":1}},"canonical_sha256":"59045869876efeb5834d6499e00cf2d05d07b2725be28cedf4dc2e1b19c141fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59045869876efeb5834d6499e00cf2d05d07b2725be28cedf4dc2e1b19c141fa","first_computed_at":"2026-07-05T05:01:44.818172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:01:44.818172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FUtMReiaaqNyWxt8NGATv+C/FhVQv4WXeAb4Rd00CO/do/Cjc+9R/ydNpuAX4OuVgSCvKlkGmdLQX8Ssh0M9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:01:44.818661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.13841","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bea437e0c4f1c41bf8ff5e9f1d3d34c0e5b34e9a83ecd932bfd683772fea745f","sha256:098b21f9d508b9a04fc4a3aa6f3e55e9325e815cb012bd492e8be2b0061d23d2"],"state_sha256":"dd0ceb9ef77fd96c60ce9f27ab2d2b1fc69f217c01597fd5937252ee4e75d362"}