{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VN2IPSBTDE2DC4Y2MDCR5NZIFT","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":"7bde8ddfe2f4d663d9cbafccf868a9d9f0f1e3250117ef3e5bf97cd85e787a31","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T16:40:22Z","title_canon_sha256":"8cf7bc7233a50272b1f9fed0c12b0132482c0a410e61b0051c0562d09780d917"},"schema_version":"1.0","source":{"id":"2404.03578","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03578","created_at":"2026-07-05T09:30:12Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03578v2","created_at":"2026-07-05T09:30:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03578","created_at":"2026-07-05T09:30:12Z"},{"alias_kind":"pith_short_12","alias_value":"VN2IPSBTDE2D","created_at":"2026-07-05T09:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"VN2IPSBTDE2DC4Y2","created_at":"2026-07-05T09:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"VN2IPSBT","created_at":"2026-07-05T09:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:afc51eff79bdc27040eb5873e85554138fc92f7b77f4c632d99961843a6d231e","target":"graph","created_at":"2026-07-05T09:30:12Z","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/2404.03578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The sim-to-real gap, which represents the disparity between training and testing environments, poses a significant challenge in reinforcement learning (RL). A promising approach to addressing this challenge is distributionally robust RL, often framed as a robust Markov decision process (RMDP). In this framework, the objective is to find a robust policy that achieves good performance under the worst-case scenario among all environments within a pre-specified uncertainty set centered around the training environment. Unlike previous work, which relies on a generative model or a pre-collected offl","authors_text":"Han Zhong, Jose Blanchet, Miao Lu, Tong Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T16:40:22Z","title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03578","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":"sha256:67974bb74f4ef036ce704b4e2e1c383221e05b73bbf929b8e9a5f8e1993b931a","target":"record","created_at":"2026-07-05T09:30:12Z","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":"7bde8ddfe2f4d663d9cbafccf868a9d9f0f1e3250117ef3e5bf97cd85e787a31","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-04T16:40:22Z","title_canon_sha256":"8cf7bc7233a50272b1f9fed0c12b0132482c0a410e61b0051c0562d09780d917"},"schema_version":"1.0","source":{"id":"2404.03578","kind":"arxiv","version":2}},"canonical_sha256":"ab7487c833193431731a60c51eb7282ce1a24f8820b437dc2de06db5b68f2bae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab7487c833193431731a60c51eb7282ce1a24f8820b437dc2de06db5b68f2bae","first_computed_at":"2026-07-05T09:30:12.153708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:12.153708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+xEeVMRVRsBEMnYCDRFfZWdFomBpe487yyicqBqTlfh3qmvgLKAbM/dYUhGIdVfek6yGVHuMFCXYoR1a2XRbDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:12.154145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03578","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67974bb74f4ef036ce704b4e2e1c383221e05b73bbf929b8e9a5f8e1993b931a","sha256:afc51eff79bdc27040eb5873e85554138fc92f7b77f4c632d99961843a6d231e"],"state_sha256":"21583d82da6a49f1b6c638fa5b11dad29005d5d0cf548d691e37e8f5270cdc9f"}