{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3ZXMLO2GA4TNAFYXGFH3EZYQB7","short_pith_number":"pith:3ZXMLO2G","schema_version":"1.0","canonical_sha256":"de6ec5bb460726d01717314fb267100fd310fe7d8dedc35530525a7f5cd2604d","source":{"kind":"arxiv","id":"2305.06657","version":3},"attestation_state":"computed","paper":{"title":"On Practical Robust Reinforcement Learning: Practical Uncertainty Set and Double-Agent Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Songnam Hong, Ukjo Hwang","submitted_at":"2023-05-11T08:52:09Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.06657","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-11T08:52:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e6c1fd0d5b7745e935dd74a730770a9ad426579f901dd5a126cb6480b19d1d32","abstract_canon_sha256":"1435fc7b05c3e8fd516786169cb0ca984133f2c410753bce1d0516deb448777c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:11.853758Z","signature_b64":"2GT7PDOChXdlIlndlYRuuBchqoXNTLTJQBYC/FX1nvb38Fjs8Fg9uAdx6GnsiavKDaHtXaK3IK3URAQl0et5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de6ec5bb460726d01717314fb267100fd310fe7d8dedc35530525a7f5cd2604d","last_reissued_at":"2026-07-05T07:14:11.853207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:11.853207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Practical Robust Reinforcement Learning: Practical Uncertainty Set and Double-Agent Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Songnam Hong, Ukjo Hwang","submitted_at":"2023-05-11T08:52:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06657","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.06657/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.06657","created_at":"2026-07-05T07:14:11.853285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06657v3","created_at":"2026-07-05T07:14:11.853285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06657","created_at":"2026-07-05T07:14:11.853285+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZXMLO2GA4TN","created_at":"2026-07-05T07:14:11.853285+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZXMLO2GA4TNAFYX","created_at":"2026-07-05T07:14:11.853285+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZXMLO2G","created_at":"2026-07-05T07:14:11.853285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZXMLO2GA4TNAFYXGFH3EZYQB7","json":"https://pith.science/pith/3ZXMLO2GA4TNAFYXGFH3EZYQB7.json","graph_json":"https://pith.science/api/pith-number/3ZXMLO2GA4TNAFYXGFH3EZYQB7/graph.json","events_json":"https://pith.science/api/pith-number/3ZXMLO2GA4TNAFYXGFH3EZYQB7/events.json","paper":"https://pith.science/paper/3ZXMLO2G"},"agent_actions":{"view_html":"https://pith.science/pith/3ZXMLO2GA4TNAFYXGFH3EZYQB7","download_json":"https://pith.science/pith/3ZXMLO2GA4TNAFYXGFH3EZYQB7.json","view_paper":"https://pith.science/paper/3ZXMLO2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06657&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZXMLO2GA4TNAFYXGFH3EZYQB7/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZXMLO2GA4TNAFYXGFH3EZYQB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZXMLO2GA4TNAFYXGFH3EZYQB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZXMLO2GA4TNAFYXGFH3EZYQB7/action/storage_attestation","attest_author":"https://pith.science/pith/3ZXMLO2GA4TNAFYXGFH3EZYQB7/action/author_attestation","sign_citation":"https://pith.science/pith/3ZXMLO2GA4TNAFYXGFH3EZYQB7/action/citation_signature","submit_replication":"https://pith.science/pith/3ZXMLO2GA4TNAFYXGFH3EZYQB7/action/replication_record"}},"created_at":"2026-07-05T07:14:11.853285+00:00","updated_at":"2026-07-05T07:14:11.853285+00:00"}