{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LIVHWWCKG53RBDAUAMY6FCJAMD","short_pith_number":"pith:LIVHWWCK","schema_version":"1.0","canonical_sha256":"5a2a7b584a3777108c140331e2892060ded32e14d7ef4acaae2e60be8e88b114","source":{"kind":"arxiv","id":"2012.04626","version":2},"attestation_state":"computed","paper":{"title":"Minimax Regret Optimisation for Robust Planning in Uncertain Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bruno Lacerda, Marc Rigter, Nick Hawes","submitted_at":"2020-12-08T18:48:14Z","abstract_excerpt":"The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs (UMDPs) capture this model ambiguity by defining sets which the parameters belong to. Minimax regret has been proposed as an objective for planning in UMDPs to find robust policies which are not overly conservative. In this work, we focus on planning for Stochastic Shortest Path (SSP) UMDPs with uncertain cost and transition functions. We introduce a Bellman equation to compute the regret for a policy. We propose a dynamic programming algorithm that utilises the regret Bellman equation, and sho"},"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":"2012.04626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-12-08T18:48:14Z","cross_cats_sorted":[],"title_canon_sha256":"acb4bdee4dcead88f859d9bed06939fa7f6c6c1024cd68d7d513a8b4b1a331dc","abstract_canon_sha256":"3fc7e0c25867e64181c9465eb817ce0995834d88c4c3246a473ca51bfbdadc45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:41.870177Z","signature_b64":"DiJYh1dV0Mi1R+94t5dEkUjDgTzTzPHInNOIAgbfLqV+/8tr6x2kP/AAgewJuHlXZ3mf8zczKHqd0L6dHeZqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a2a7b584a3777108c140331e2892060ded32e14d7ef4acaae2e60be8e88b114","last_reissued_at":"2026-07-05T05:40:41.869772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:41.869772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimax Regret Optimisation for Robust Planning in Uncertain Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bruno Lacerda, Marc Rigter, Nick Hawes","submitted_at":"2020-12-08T18:48:14Z","abstract_excerpt":"The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs (UMDPs) capture this model ambiguity by defining sets which the parameters belong to. Minimax regret has been proposed as an objective for planning in UMDPs to find robust policies which are not overly conservative. In this work, we focus on planning for Stochastic Shortest Path (SSP) UMDPs with uncertain cost and transition functions. We introduce a Bellman equation to compute the regret for a policy. We propose a dynamic programming algorithm that utilises the regret Bellman equation, and sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04626","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/2012.04626/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":"2012.04626","created_at":"2026-07-05T05:40:41.869830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.04626v2","created_at":"2026-07-05T05:40:41.869830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04626","created_at":"2026-07-05T05:40:41.869830+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIVHWWCKG53R","created_at":"2026-07-05T05:40:41.869830+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIVHWWCKG53RBDAU","created_at":"2026-07-05T05:40:41.869830+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIVHWWCK","created_at":"2026-07-05T05:40:41.869830+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/LIVHWWCKG53RBDAUAMY6FCJAMD","json":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD.json","graph_json":"https://pith.science/api/pith-number/LIVHWWCKG53RBDAUAMY6FCJAMD/graph.json","events_json":"https://pith.science/api/pith-number/LIVHWWCKG53RBDAUAMY6FCJAMD/events.json","paper":"https://pith.science/paper/LIVHWWCK"},"agent_actions":{"view_html":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD","download_json":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD.json","view_paper":"https://pith.science/paper/LIVHWWCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.04626&json=true","fetch_graph":"https://pith.science/api/pith-number/LIVHWWCKG53RBDAUAMY6FCJAMD/graph.json","fetch_events":"https://pith.science/api/pith-number/LIVHWWCKG53RBDAUAMY6FCJAMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/action/storage_attestation","attest_author":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/action/author_attestation","sign_citation":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/action/citation_signature","submit_replication":"https://pith.science/pith/LIVHWWCKG53RBDAUAMY6FCJAMD/action/replication_record"}},"created_at":"2026-07-05T05:40:41.869830+00:00","updated_at":"2026-07-05T05:40:41.869830+00:00"}