{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GI7JMQ6K6UC4F7M3XTAILVZ6HV","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":"340aa470b7b62da3ba854e6a0dbd1d334b86d5cab7abf3f2d8f78d1de480142a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-20T17:14:14Z","title_canon_sha256":"3c33a85efd4ddacaa17bb283eaa473c98efc2c4718b7dafc089ea0a71ad64cf2"},"schema_version":"1.0","source":{"id":"2212.10439","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10439","created_at":"2026-07-05T08:18:40Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10439v2","created_at":"2026-07-05T08:18:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10439","created_at":"2026-07-05T08:18:40Z"},{"alias_kind":"pith_short_12","alias_value":"GI7JMQ6K6UC4","created_at":"2026-07-05T08:18:40Z"},{"alias_kind":"pith_short_16","alias_value":"GI7JMQ6K6UC4F7M3","created_at":"2026-07-05T08:18:40Z"},{"alias_kind":"pith_short_8","alias_value":"GI7JMQ6K","created_at":"2026-07-05T08:18:40Z"}],"graph_snapshots":[{"event_id":"sha256:3b30580196bfae9a9dc891a92f1378072e6cb158e1a679fe57919c8eaa72dd10","target":"graph","created_at":"2026-07-05T08:18:40Z","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/2212.10439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust Markov decision processes (RMDPs) provide a promising framework for computing reliable policies in the face of model errors. Many successful reinforcement learning algorithms build on variations of policy-gradient methods, but adapting these methods to RMDPs has been challenging. As a result, the applicability of RMDPs to large, practical domains remains limited. This paper proposes a new Double-Loop Robust Policy Gradient (DRPG), the first generic policy gradient method for RMDPs. In contrast with prior robust policy gradient algorithms, DRPG monotonically reduces approximation errors ","authors_text":"Chin Pang Ho, Marek Petrik, Qiuhao Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-20T17:14:14Z","title":"Policy Gradient in Robust MDPs with Global Convergence Guarantee"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10439","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:bdaae8fa5635510b1caa9cdb90ef4021de147e1a2a9ed57a2cb042d41bee05a0","target":"record","created_at":"2026-07-05T08:18:40Z","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":"340aa470b7b62da3ba854e6a0dbd1d334b86d5cab7abf3f2d8f78d1de480142a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-20T17:14:14Z","title_canon_sha256":"3c33a85efd4ddacaa17bb283eaa473c98efc2c4718b7dafc089ea0a71ad64cf2"},"schema_version":"1.0","source":{"id":"2212.10439","kind":"arxiv","version":2}},"canonical_sha256":"323e9643caf505c2fd9bbcc085d73e3d4d6178a483955817d09811eeee12ea83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"323e9643caf505c2fd9bbcc085d73e3d4d6178a483955817d09811eeee12ea83","first_computed_at":"2026-07-05T08:18:40.192520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:40.192520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SgRaJv5g1jRMeQ+rY/cVxlyeBuP8qeA2f6Icrui094FnDwDIqStiKvWZ8PNJiXr7WiJ+EZtmqE6CAfkQN3bxBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:40.193033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10439","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bdaae8fa5635510b1caa9cdb90ef4021de147e1a2a9ed57a2cb042d41bee05a0","sha256:3b30580196bfae9a9dc891a92f1378072e6cb158e1a679fe57919c8eaa72dd10"],"state_sha256":"13c89520d51753fbde5455d856cef5d98a6453e52cfe32473dd392eedd0d9629"}