{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:A26B3KL4PLUFYYGCEXECY5HJYT","short_pith_number":"pith:A26B3KL4","schema_version":"1.0","canonical_sha256":"06bc1da97c7ae85c60c225c82c74e9c4ef22b526086bd3fa4630f775ed705b49","source":{"kind":"arxiv","id":"1705.03597","version":1},"attestation_state":"computed","paper":{"title":"Solving Multi-Objective MDP with Lexicographic Preference: An application to stochastic planning with multiple quantile objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Yan Li, Zhaohan Sun","submitted_at":"2017-05-10T03:13:30Z","abstract_excerpt":"In most common settings of Markov Decision Process (MDP), an agent evaluate a policy based on expectation of (discounted) sum of rewards. However in many applications this criterion might not be suitable from two perspective: first, in risk aversion situation expectation of accumulated rewards is not robust enough, this is the case when distribution of accumulated reward is heavily skewed; another issue is that many applications naturally take several objective into consideration when evaluating a policy, for instance in autonomous driving an agent needs to balance speed and safety when choosi"},"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":"1705.03597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-05-10T03:13:30Z","cross_cats_sorted":[],"title_canon_sha256":"1103f0c9ee3ab88c754c817442905e54491a9b7832837ad1d83273ee3e9ae360","abstract_canon_sha256":"5b02c58d31f82849da9e0dc31e8feaeb4faad8ec34de261485950c267ebd0ddb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:43.495490Z","signature_b64":"D/UZ/00iXO9efodfY/+pHf4jFLwEwQ/VddWgP9ge0Ol7euFWOMiqtw3ydrdMfLPnY0b6euSZrGJ1D3WBbwVeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06bc1da97c7ae85c60c225c82c74e9c4ef22b526086bd3fa4630f775ed705b49","last_reissued_at":"2026-05-18T00:44:43.495054Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:43.495054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Multi-Objective MDP with Lexicographic Preference: An application to stochastic planning with multiple quantile objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Yan Li, Zhaohan Sun","submitted_at":"2017-05-10T03:13:30Z","abstract_excerpt":"In most common settings of Markov Decision Process (MDP), an agent evaluate a policy based on expectation of (discounted) sum of rewards. However in many applications this criterion might not be suitable from two perspective: first, in risk aversion situation expectation of accumulated rewards is not robust enough, this is the case when distribution of accumulated reward is heavily skewed; another issue is that many applications naturally take several objective into consideration when evaluating a policy, for instance in autonomous driving an agent needs to balance speed and safety when choosi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03597","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":"1705.03597","created_at":"2026-05-18T00:44:43.495115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.03597v1","created_at":"2026-05-18T00:44:43.495115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03597","created_at":"2026-05-18T00:44:43.495115+00:00"},{"alias_kind":"pith_short_12","alias_value":"A26B3KL4PLUF","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"A26B3KL4PLUFYYGC","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"A26B3KL4","created_at":"2026-05-18T12:31:05.417338+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/A26B3KL4PLUFYYGCEXECY5HJYT","json":"https://pith.science/pith/A26B3KL4PLUFYYGCEXECY5HJYT.json","graph_json":"https://pith.science/api/pith-number/A26B3KL4PLUFYYGCEXECY5HJYT/graph.json","events_json":"https://pith.science/api/pith-number/A26B3KL4PLUFYYGCEXECY5HJYT/events.json","paper":"https://pith.science/paper/A26B3KL4"},"agent_actions":{"view_html":"https://pith.science/pith/A26B3KL4PLUFYYGCEXECY5HJYT","download_json":"https://pith.science/pith/A26B3KL4PLUFYYGCEXECY5HJYT.json","view_paper":"https://pith.science/paper/A26B3KL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.03597&json=true","fetch_graph":"https://pith.science/api/pith-number/A26B3KL4PLUFYYGCEXECY5HJYT/graph.json","fetch_events":"https://pith.science/api/pith-number/A26B3KL4PLUFYYGCEXECY5HJYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A26B3KL4PLUFYYGCEXECY5HJYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A26B3KL4PLUFYYGCEXECY5HJYT/action/storage_attestation","attest_author":"https://pith.science/pith/A26B3KL4PLUFYYGCEXECY5HJYT/action/author_attestation","sign_citation":"https://pith.science/pith/A26B3KL4PLUFYYGCEXECY5HJYT/action/citation_signature","submit_replication":"https://pith.science/pith/A26B3KL4PLUFYYGCEXECY5HJYT/action/replication_record"}},"created_at":"2026-05-18T00:44:43.495115+00:00","updated_at":"2026-05-18T00:44:43.495115+00:00"}