{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IOGZPBAXIINCQJHPBUKYLZI7RT","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":"45835b25690326b680153caf6f52389937e890b1822f602808935d221fc0bd35","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-14T07:27:30Z","title_canon_sha256":"c197bb70824d2684b1930d8ebc9365c356f7cda47af55d6009ea90428b2b799e"},"schema_version":"1.0","source":{"id":"2402.08991","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08991","created_at":"2026-07-05T08:46:21Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08991v3","created_at":"2026-07-05T08:46:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08991","created_at":"2026-07-05T08:46:21Z"},{"alias_kind":"pith_short_12","alias_value":"IOGZPBAXIINC","created_at":"2026-07-05T08:46:21Z"},{"alias_kind":"pith_short_16","alias_value":"IOGZPBAXIINCQJHP","created_at":"2026-07-05T08:46:21Z"},{"alias_kind":"pith_short_8","alias_value":"IOGZPBAX","created_at":"2026-07-05T08:46:21Z"}],"graph_snapshots":[{"event_id":"sha256:57674e301cd8796946e7a2ab636743e72eb8133abf7c63fa8aaa7a41911a5f4d","target":"graph","created_at":"2026-07-05T08:46:21Z","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/2402.08991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study tackles the challenges of adversarial corruption in model-based reinforcement learning (RL), where the transition dynamics can be corrupted by an adversary. Existing studies on corruption-robust RL mostly focus on the setting of model-free RL, where robust least-square regression is often employed for value function estimation. However, these techniques cannot be directly applied to model-based RL. In this paper, we focus on model-based RL and take the maximum likelihood estimation (MLE) approach to learn transition model. Our work encompasses both online and offline settings. In th","authors_text":"Chenlu Ye, Jiafan He, Quanquan Gu, Tong Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-14T07:27:30Z","title":"Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08991","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:d683e5395a20e2f2353339d559182586e863fe534e3cd87e1df9bd0c9326c6eb","target":"record","created_at":"2026-07-05T08:46:21Z","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":"45835b25690326b680153caf6f52389937e890b1822f602808935d221fc0bd35","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-14T07:27:30Z","title_canon_sha256":"c197bb70824d2684b1930d8ebc9365c356f7cda47af55d6009ea90428b2b799e"},"schema_version":"1.0","source":{"id":"2402.08991","kind":"arxiv","version":3}},"canonical_sha256":"438d978417421a2824ef0d1585e51f8cc88d2092c75f3af4831fff8e83483901","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"438d978417421a2824ef0d1585e51f8cc88d2092c75f3af4831fff8e83483901","first_computed_at":"2026-07-05T08:46:21.448020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:21.448020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"It9gJ+01vAF0PJad/NwCSTQzvEnEUobqIB23VooTJb7LOQbKacuQv3p6Oa0X4oMbzpgsaNY84vk5tIMaqB4NAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:21.448444Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08991","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d683e5395a20e2f2353339d559182586e863fe534e3cd87e1df9bd0c9326c6eb","sha256:57674e301cd8796946e7a2ab636743e72eb8133abf7c63fa8aaa7a41911a5f4d"],"state_sha256":"ebb1189fff2d93bb9750ce0b990c5b6fbdbd19c615bda0d4467cfc8e8ebf595c"}