{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3ZXMLO2GA4TNAFYXGFH3EZYQB7","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":"1435fc7b05c3e8fd516786169cb0ca984133f2c410753bce1d0516deb448777c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-11T08:52:09Z","title_canon_sha256":"e6c1fd0d5b7745e935dd74a730770a9ad426579f901dd5a126cb6480b19d1d32"},"schema_version":"1.0","source":{"id":"2305.06657","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06657","created_at":"2026-07-05T07:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06657v3","created_at":"2026-07-05T07:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06657","created_at":"2026-07-05T07:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"3ZXMLO2GA4TN","created_at":"2026-07-05T07:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"3ZXMLO2GA4TNAFYX","created_at":"2026-07-05T07:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"3ZXMLO2G","created_at":"2026-07-05T07:14:11Z"}],"graph_snapshots":[{"event_id":"sha256:c4b7481b332a915ff9fcc0181f2220753abcf33989cce6af7cff12205a7f89a7","target":"graph","created_at":"2026-07-05T07:14:11Z","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/2305.06657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust reinforcement learning (RRL) aims at seeking a robust policy to optimize the worst case performance over an uncertainty set of Markov decision processes (MDPs). This set contains some perturbed MDPs from a nominal MDP (N-MDP) that generate samples for training, which reflects some potential mismatches between training (i.e., N-MDP) and true environments. In this paper we present an elaborated uncertainty set by excluding some implausible MDPs from the existing sets. Under this uncertainty set, we develop a sample-based RRL algorithm (named ARQ-Learning) for tabular setting and character","authors_text":"Songnam Hong, Ukjo Hwang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-11T08:52:09Z","title":"On Practical Robust Reinforcement Learning: Practical Uncertainty Set and Double-Agent Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06657","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":"sha256:2480631d80132c25f5067c0ad98b280954f1b7e863a817372420ae89a1ef253a","target":"record","created_at":"2026-07-05T07:14:11Z","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":"1435fc7b05c3e8fd516786169cb0ca984133f2c410753bce1d0516deb448777c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-11T08:52:09Z","title_canon_sha256":"e6c1fd0d5b7745e935dd74a730770a9ad426579f901dd5a126cb6480b19d1d32"},"schema_version":"1.0","source":{"id":"2305.06657","kind":"arxiv","version":3}},"canonical_sha256":"de6ec5bb460726d01717314fb267100fd310fe7d8dedc35530525a7f5cd2604d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de6ec5bb460726d01717314fb267100fd310fe7d8dedc35530525a7f5cd2604d","first_computed_at":"2026-07-05T07:14:11.853207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:11.853207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2GT7PDOChXdlIlndlYRuuBchqoXNTLTJQBYC/FX1nvb38Fjs8Fg9uAdx6GnsiavKDaHtXaK3IK3URAQl0et5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:11.853758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.06657","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2480631d80132c25f5067c0ad98b280954f1b7e863a817372420ae89a1ef253a","sha256:c4b7481b332a915ff9fcc0181f2220753abcf33989cce6af7cff12205a7f89a7"],"state_sha256":"f2a4512ea4e323bd50cfc7fef32676e5afad4c4006296ca9effa41a1fc4b60c6"}