{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:WBDY2OWY6EZWSEGAIW2QA53UDM","short_pith_number":"pith:WBDY2OWY","schema_version":"1.0","canonical_sha256":"b0478d3ad8f1336910c045b50077741b2597e71bbb274f1543a5b024c55f797f","source":{"kind":"arxiv","id":"1205.2619","version":1},"attestation_state":"computed","paper":{"title":"Regret-based Reward Elicitation for Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Craig Boutilier, Kevin Regan","submitted_at":"2012-05-09T18:23:30Z","abstract_excerpt":"The specification of aMarkov decision process (MDP) can be difficult. Reward function specification is especially problematic; in practice, it is often cognitively complex and time-consuming for users to precisely specify rewards. This work casts the problem of specifying rewards as one of preference elicitation and aims to minimize the degree of precision with which a reward function must be specified while still allowing optimal or near-optimal policies to be produced. We first discuss how robust policies can be computed for MDPs given only partial reward information using the minimax regret"},"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":"1205.2619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-05-09T18:23:30Z","cross_cats_sorted":[],"title_canon_sha256":"3c098a73875e50cde252bcac4bedc421067c6b375ae0487eb014c1c071516442","abstract_canon_sha256":"d51ff6f7800535574eca076607013c52676bad8c3e7a9f77b04c44f0aa9c5e3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:55:47.880334Z","signature_b64":"Jt61hCMWaxCoezNW4kF0W4CcOWuJk6BjC/BsoPZEOUkjvufCc2z9jzS061DTbhb2onsiCfu9kRbxnQv8QmTqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0478d3ad8f1336910c045b50077741b2597e71bbb274f1543a5b024c55f797f","last_reissued_at":"2026-05-18T03:55:47.879831Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:55:47.879831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regret-based Reward Elicitation for Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Craig Boutilier, Kevin Regan","submitted_at":"2012-05-09T18:23:30Z","abstract_excerpt":"The specification of aMarkov decision process (MDP) can be difficult. Reward function specification is especially problematic; in practice, it is often cognitively complex and time-consuming for users to precisely specify rewards. This work casts the problem of specifying rewards as one of preference elicitation and aims to minimize the degree of precision with which a reward function must be specified while still allowing optimal or near-optimal policies to be produced. We first discuss how robust policies can be computed for MDPs given only partial reward information using the minimax regret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.2619","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1205.2619","created_at":"2026-05-18T03:55:47.879924+00:00"},{"alias_kind":"arxiv_version","alias_value":"1205.2619v1","created_at":"2026-05-18T03:55:47.879924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.2619","created_at":"2026-05-18T03:55:47.879924+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBDY2OWY6EZW","created_at":"2026-05-18T12:27:25.539911+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBDY2OWY6EZWSEGA","created_at":"2026-05-18T12:27:25.539911+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBDY2OWY","created_at":"2026-05-18T12:27:25.539911+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/WBDY2OWY6EZWSEGAIW2QA53UDM","json":"https://pith.science/pith/WBDY2OWY6EZWSEGAIW2QA53UDM.json","graph_json":"https://pith.science/api/pith-number/WBDY2OWY6EZWSEGAIW2QA53UDM/graph.json","events_json":"https://pith.science/api/pith-number/WBDY2OWY6EZWSEGAIW2QA53UDM/events.json","paper":"https://pith.science/paper/WBDY2OWY"},"agent_actions":{"view_html":"https://pith.science/pith/WBDY2OWY6EZWSEGAIW2QA53UDM","download_json":"https://pith.science/pith/WBDY2OWY6EZWSEGAIW2QA53UDM.json","view_paper":"https://pith.science/paper/WBDY2OWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1205.2619&json=true","fetch_graph":"https://pith.science/api/pith-number/WBDY2OWY6EZWSEGAIW2QA53UDM/graph.json","fetch_events":"https://pith.science/api/pith-number/WBDY2OWY6EZWSEGAIW2QA53UDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBDY2OWY6EZWSEGAIW2QA53UDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBDY2OWY6EZWSEGAIW2QA53UDM/action/storage_attestation","attest_author":"https://pith.science/pith/WBDY2OWY6EZWSEGAIW2QA53UDM/action/author_attestation","sign_citation":"https://pith.science/pith/WBDY2OWY6EZWSEGAIW2QA53UDM/action/citation_signature","submit_replication":"https://pith.science/pith/WBDY2OWY6EZWSEGAIW2QA53UDM/action/replication_record"}},"created_at":"2026-05-18T03:55:47.879924+00:00","updated_at":"2026-05-18T03:55:47.879924+00:00"}