{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IXAJRHB4M443GTBCP4LZJEBIII","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":"b2cabde6151d4874d15d88f5bf3c010ef42f6f231586816fb674e48a6684ff03","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T08:11:15Z","title_canon_sha256":"ecfac0e5c86a2c0c981138f8f211f3415a16284970e69845a48fa7f6adc46042"},"schema_version":"1.0","source":{"id":"2507.03372","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03372","created_at":"2026-07-05T11:31:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03372v1","created_at":"2026-07-05T11:31:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03372","created_at":"2026-07-05T11:31:58Z"},{"alias_kind":"pith_short_12","alias_value":"IXAJRHB4M443","created_at":"2026-07-05T11:31:58Z"},{"alias_kind":"pith_short_16","alias_value":"IXAJRHB4M443GTBC","created_at":"2026-07-05T11:31:58Z"},{"alias_kind":"pith_short_8","alias_value":"IXAJRHB4","created_at":"2026-07-05T11:31:58Z"}],"graph_snapshots":[{"event_id":"sha256:81e1184659be251d656d2a58327620a663769dfbd7a8d3a59337bd9d049dbfa1","target":"graph","created_at":"2026-07-05T11:31:58Z","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/2507.03372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different perturbations, raising concerns about their effectiveness and safety in real-world applications. In this work, we focus on the robustness of RL policies against action perturbations and introduce a novel framework called Optimal Adversary-aware Policy Iteration (OA-PI). Our framework enhances action robustness under various perturbations by evaluating and improving policy performance against the corresponding optimal adver","authors_text":"Buqing Nie, Jingtian Ji, Yangqing Fu, Yue Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T08:11:15Z","title":"Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03372","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":"sha256:792a802b632c64386fd2ce9e23ee1846aef304c0677656126088e696d739c82c","target":"record","created_at":"2026-07-05T11:31:58Z","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":"b2cabde6151d4874d15d88f5bf3c010ef42f6f231586816fb674e48a6684ff03","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T08:11:15Z","title_canon_sha256":"ecfac0e5c86a2c0c981138f8f211f3415a16284970e69845a48fa7f6adc46042"},"schema_version":"1.0","source":{"id":"2507.03372","kind":"arxiv","version":1}},"canonical_sha256":"45c0989c3c6739b34c227f17949028421038a772d4269e17132d273139a9842b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45c0989c3c6739b34c227f17949028421038a772d4269e17132d273139a9842b","first_computed_at":"2026-07-05T11:31:58.327972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:58.327972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H46QWOUc+TlQK9mI11vjYb7t+J6CrW9JllGpgktvSusjUw5rDMPuWXZR92YYYeQVGIUQKSE8uT+4ppF13ZpHDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:58.328525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03372","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:792a802b632c64386fd2ce9e23ee1846aef304c0677656126088e696d739c82c","sha256:81e1184659be251d656d2a58327620a663769dfbd7a8d3a59337bd9d049dbfa1"],"state_sha256":"125d185142076fbbd61e34fd789d4b3a01e9dc30a69ca0c77f56d4204e0a2e45"}