{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6FUG7SOECA52IGUOFVMWTMFBHO","short_pith_number":"pith:6FUG7SOE","schema_version":"1.0","canonical_sha256":"f1686fc9c4103ba41a8e2d5969b0a13b9e0da0ca25053c1032bdf6c6202f95af","source":{"kind":"arxiv","id":"2312.13912","version":2},"attestation_state":"computed","paper":{"title":"Solving Long-run Average Reward Robust MDPs via Stochastic Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"{\\DJ}or{\\dj}e \\v{Z}ikeli\\'c, Ehsan Kafshdar Goharshady, Krishnendu Chatterjee, Mehrdad Karrabi, Petr Novotn\\'y","submitted_at":"2023-12-21T15:00:06Z","abstract_excerpt":"Markov decision processes (MDPs) provide a standard framework for sequential decision making under uncertainty. However, MDPs do not take uncertainty in transition probabilities into account. Robust Markov decision processes (RMDPs) address this shortcoming of MDPs by assigning to each transition an uncertainty set rather than a single probability value. In this work, we consider polytopic RMDPs in which all uncertainty sets are polytopes and study the problem of solving long-run average reward polytopic RMDPs. We present a novel perspective on this problem and show that it can be reduced to s"},"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":"2312.13912","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-21T15:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"13cb07ae14b0c27ac3d1437cdc5fde9b95ccb63a7cd59f2e23654ab9167c06eb","abstract_canon_sha256":"89cb8e5ffa32329e0ef07708cfc952d444a1400a17145544d2197658f36e9bed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:52.905341Z","signature_b64":"8UsUnbDT4Faof7WmLuAxh+OxxlXU6I/dkbJBY0lRl8FOEkHMsQBex5FDCfhTgvKV+LKYQtVAPCATsxfO5E9CDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1686fc9c4103ba41a8e2d5969b0a13b9e0da0ca25053c1032bdf6c6202f95af","last_reissued_at":"2026-07-05T08:13:52.904823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:52.904823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Long-run Average Reward Robust MDPs via Stochastic Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"{\\DJ}or{\\dj}e \\v{Z}ikeli\\'c, Ehsan Kafshdar Goharshady, Krishnendu Chatterjee, Mehrdad Karrabi, Petr Novotn\\'y","submitted_at":"2023-12-21T15:00:06Z","abstract_excerpt":"Markov decision processes (MDPs) provide a standard framework for sequential decision making under uncertainty. However, MDPs do not take uncertainty in transition probabilities into account. Robust Markov decision processes (RMDPs) address this shortcoming of MDPs by assigning to each transition an uncertainty set rather than a single probability value. In this work, we consider polytopic RMDPs in which all uncertainty sets are polytopes and study the problem of solving long-run average reward polytopic RMDPs. We present a novel perspective on this problem and show that it can be reduced to s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13912","kind":"arxiv","version":2},"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/2312.13912/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":"2312.13912","created_at":"2026-07-05T08:13:52.904878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13912v2","created_at":"2026-07-05T08:13:52.904878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13912","created_at":"2026-07-05T08:13:52.904878+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FUG7SOECA52","created_at":"2026-07-05T08:13:52.904878+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FUG7SOECA52IGUO","created_at":"2026-07-05T08:13:52.904878+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FUG7SOE","created_at":"2026-07-05T08:13:52.904878+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/6FUG7SOECA52IGUOFVMWTMFBHO","json":"https://pith.science/pith/6FUG7SOECA52IGUOFVMWTMFBHO.json","graph_json":"https://pith.science/api/pith-number/6FUG7SOECA52IGUOFVMWTMFBHO/graph.json","events_json":"https://pith.science/api/pith-number/6FUG7SOECA52IGUOFVMWTMFBHO/events.json","paper":"https://pith.science/paper/6FUG7SOE"},"agent_actions":{"view_html":"https://pith.science/pith/6FUG7SOECA52IGUOFVMWTMFBHO","download_json":"https://pith.science/pith/6FUG7SOECA52IGUOFVMWTMFBHO.json","view_paper":"https://pith.science/paper/6FUG7SOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13912&json=true","fetch_graph":"https://pith.science/api/pith-number/6FUG7SOECA52IGUOFVMWTMFBHO/graph.json","fetch_events":"https://pith.science/api/pith-number/6FUG7SOECA52IGUOFVMWTMFBHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FUG7SOECA52IGUOFVMWTMFBHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FUG7SOECA52IGUOFVMWTMFBHO/action/storage_attestation","attest_author":"https://pith.science/pith/6FUG7SOECA52IGUOFVMWTMFBHO/action/author_attestation","sign_citation":"https://pith.science/pith/6FUG7SOECA52IGUOFVMWTMFBHO/action/citation_signature","submit_replication":"https://pith.science/pith/6FUG7SOECA52IGUOFVMWTMFBHO/action/replication_record"}},"created_at":"2026-07-05T08:13:52.904878+00:00","updated_at":"2026-07-05T08:13:52.904878+00:00"}