{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3IKMYQI365UIGWU6RMUYPKOLEQ","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":"df1e2efc5ff1facb982a9a6d7b30f4a7de820b568abb7896f8fb4b3ee80d33c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-11T01:48:38Z","title_canon_sha256":"d54545140528394a991db5fdd479aed96d50c84141f69a2ad42f0bae03e41b7a"},"schema_version":"1.0","source":{"id":"2102.05800","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.05800","created_at":"2026-07-05T02:47:04Z"},{"alias_kind":"arxiv_version","alias_value":"2102.05800v3","created_at":"2026-07-05T02:47:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05800","created_at":"2026-07-05T02:47:04Z"},{"alias_kind":"pith_short_12","alias_value":"3IKMYQI365UI","created_at":"2026-07-05T02:47:04Z"},{"alias_kind":"pith_short_16","alias_value":"3IKMYQI365UIGWU6","created_at":"2026-07-05T02:47:04Z"},{"alias_kind":"pith_short_8","alias_value":"3IKMYQI3","created_at":"2026-07-05T02:47:04Z"}],"graph_snapshots":[{"event_id":"sha256:7c2757cf4fd169db9c4e1df280a044a07dd8a5bba5e6c85586c535c2a780c1f8","target":"graph","created_at":"2026-07-05T02:47:04Z","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/2102.05800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of robust reinforcement learning under adversarial corruption on both rewards and transitions. Our attack model assumes an \\textit{adaptive} adversary who can arbitrarily corrupt the reward and transition at every step within an episode, for at most $\\epsilon$-fraction of the learning episodes. Our attack model is strictly stronger than those considered in prior works. Our first result shows that no algorithm can find a better than $O(\\epsilon)$-optimal policy under our attack model. Next, we show that surprisingly the natural policy gradient (NPG) method retains a natural","authors_text":"Wen Sun, Xiaojin Zhu, Xuezhou Zhang, Yiding Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-11T01:48:38Z","title":"Robust Policy Gradient against Strong Data Corruption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05800","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":"sha256:69bad10a19c55aecca6725e479bae49ed5ffa021f958a3a7a9d19968c569badd","target":"record","created_at":"2026-07-05T02:47:04Z","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":"df1e2efc5ff1facb982a9a6d7b30f4a7de820b568abb7896f8fb4b3ee80d33c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-11T01:48:38Z","title_canon_sha256":"d54545140528394a991db5fdd479aed96d50c84141f69a2ad42f0bae03e41b7a"},"schema_version":"1.0","source":{"id":"2102.05800","kind":"arxiv","version":3}},"canonical_sha256":"da14cc411bf768835a9e8b2987a9cb240397679a8970a97efe7ca4c03deaa6c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da14cc411bf768835a9e8b2987a9cb240397679a8970a97efe7ca4c03deaa6c6","first_computed_at":"2026-07-05T02:47:04.847075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:04.847075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4uF0z5xD87x3fKbw1nybCy1+LB/gKyYCMBR7SUsvDrd6YqOgjpfTMqw0RPWW6WicG47/W5THwGMcqn56FkiiAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:04.847521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.05800","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69bad10a19c55aecca6725e479bae49ed5ffa021f958a3a7a9d19968c569badd","sha256:7c2757cf4fd169db9c4e1df280a044a07dd8a5bba5e6c85586c535c2a780c1f8"],"state_sha256":"3ae4a3ec2fcb539c63709b7d3aaae925dda2997594edd62abb0983728709902c"}