{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CFKICQAVOWSKTENGKF2EIXOQET","short_pith_number":"pith:CFKICQAV","schema_version":"1.0","canonical_sha256":"115481401575a4a991a65174445dd024e153268c8a8d1d8018f5de19b39669e0","source":{"kind":"arxiv","id":"2311.09018","version":4},"attestation_state":"computed","paper":{"title":"On the Foundation of Distributionally Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jose Blanchet, Nian Si, Shengbo Wang, Zhengyuan Zhou","submitted_at":"2023-11-15T15:02:23Z","abstract_excerpt":"Motivated by the need for a robust policy in the face of environment shifts between training and deployment, we contribute to the theoretical foundation of distributionally robust reinforcement learning (DRRL). This is accomplished through a comprehensive modeling framework centered around robust Markov decision processes (RMDPs). This framework obliges the decision maker to choose an optimal policy under the worst-case distributional shift orchestrated by an adversary. By unifying and extending existing formulations, we rigorously construct RMDPs that embrace various modeling attributes for b"},"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":"2311.09018","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-15T15:02:23Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"57aa3295f0bbbeb07a493091ba443207b0096c53a0b21b30a786af0bba7c7183","abstract_canon_sha256":"1678b515a2130eb1439001f625e4a9e864c8236ce4b749419d638d3e776acbe4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:16.479102Z","signature_b64":"NNTlledknVRIeXvBEV4sBrJ8fC+g6tA0JDR5lO+x5dD8ClkwNwQ1/nQrG7H+RXNknwfQwoETLkmkdw3oMn2yBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"115481401575a4a991a65174445dd024e153268c8a8d1d8018f5de19b39669e0","last_reissued_at":"2026-07-05T11:58:16.478656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:16.478656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Foundation of Distributionally Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jose Blanchet, Nian Si, Shengbo Wang, Zhengyuan Zhou","submitted_at":"2023-11-15T15:02:23Z","abstract_excerpt":"Motivated by the need for a robust policy in the face of environment shifts between training and deployment, we contribute to the theoretical foundation of distributionally robust reinforcement learning (DRRL). This is accomplished through a comprehensive modeling framework centered around robust Markov decision processes (RMDPs). This framework obliges the decision maker to choose an optimal policy under the worst-case distributional shift orchestrated by an adversary. By unifying and extending existing formulations, we rigorously construct RMDPs that embrace various modeling attributes for b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09018","kind":"arxiv","version":4},"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/2311.09018/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":"2311.09018","created_at":"2026-07-05T11:58:16.478712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09018v4","created_at":"2026-07-05T11:58:16.478712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09018","created_at":"2026-07-05T11:58:16.478712+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFKICQAVOWSK","created_at":"2026-07-05T11:58:16.478712+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFKICQAVOWSKTENG","created_at":"2026-07-05T11:58:16.478712+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFKICQAV","created_at":"2026-07-05T11:58:16.478712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14444","citing_title":"Statistical and Algorithmic Foundations of Reinforcement Learning","ref_index":125,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFKICQAVOWSKTENGKF2EIXOQET","json":"https://pith.science/pith/CFKICQAVOWSKTENGKF2EIXOQET.json","graph_json":"https://pith.science/api/pith-number/CFKICQAVOWSKTENGKF2EIXOQET/graph.json","events_json":"https://pith.science/api/pith-number/CFKICQAVOWSKTENGKF2EIXOQET/events.json","paper":"https://pith.science/paper/CFKICQAV"},"agent_actions":{"view_html":"https://pith.science/pith/CFKICQAVOWSKTENGKF2EIXOQET","download_json":"https://pith.science/pith/CFKICQAVOWSKTENGKF2EIXOQET.json","view_paper":"https://pith.science/paper/CFKICQAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09018&json=true","fetch_graph":"https://pith.science/api/pith-number/CFKICQAVOWSKTENGKF2EIXOQET/graph.json","fetch_events":"https://pith.science/api/pith-number/CFKICQAVOWSKTENGKF2EIXOQET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFKICQAVOWSKTENGKF2EIXOQET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFKICQAVOWSKTENGKF2EIXOQET/action/storage_attestation","attest_author":"https://pith.science/pith/CFKICQAVOWSKTENGKF2EIXOQET/action/author_attestation","sign_citation":"https://pith.science/pith/CFKICQAVOWSKTENGKF2EIXOQET/action/citation_signature","submit_replication":"https://pith.science/pith/CFKICQAVOWSKTENGKF2EIXOQET/action/replication_record"}},"created_at":"2026-07-05T11:58:16.478712+00:00","updated_at":"2026-07-05T11:58:16.478712+00:00"}