{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BQET4DP4CGLGSH5HBGVPZA77ST","short_pith_number":"pith:BQET4DP4","schema_version":"1.0","canonical_sha256":"0c093e0dfc1196691fa709aafc83ff94f1a00399547a4c2f5eded4ebecd39007","source":{"kind":"arxiv","id":"2211.13032","version":2},"attestation_state":"computed","paper":{"title":"Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Conor F. Hayes, Diederik M. Roijers, Enda Howley, Mathieu Reymond, Patrick Mannion","submitted_at":"2022-11-23T15:33:19Z","abstract_excerpt":"In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from a single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For example, in a medical setting a patient may only have one opportunity to treat their illness. Making decisions using just the expected future returns -- known in reinforcement learning as the value -- cannot account for the potential range of adverse or positive outcomes a decision may have. Therefore, we should use the distribution over expected future returns"},"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":"2211.13032","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-11-23T15:33:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"14245cb4acae416124bbef7058522e6d2533e3d1c4e843fb8f7b204a0b295d5b","abstract_canon_sha256":"85361b663ee384041e6f38b7e2c80fc94433016cbbe8941f245c54c005db6526"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:31.077372Z","signature_b64":"ZDCbub31aThG0NaJLZ7mPXH4C584sSQ23fSksG6sei14WNTi0p4wOOvK5dYPaHkfMyj7eyCnRoSyjCWMns60BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c093e0dfc1196691fa709aafc83ff94f1a00399547a4c2f5eded4ebecd39007","last_reissued_at":"2026-07-05T05:22:31.076970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:31.076970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Conor F. Hayes, Diederik M. Roijers, Enda Howley, Mathieu Reymond, Patrick Mannion","submitted_at":"2022-11-23T15:33:19Z","abstract_excerpt":"In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from a single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For example, in a medical setting a patient may only have one opportunity to treat their illness. Making decisions using just the expected future returns -- known in reinforcement learning as the value -- cannot account for the potential range of adverse or positive outcomes a decision may have. Therefore, we should use the distribution over expected future returns"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13032","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/2211.13032/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":"2211.13032","created_at":"2026-07-05T05:22:31.077027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13032v2","created_at":"2026-07-05T05:22:31.077027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13032","created_at":"2026-07-05T05:22:31.077027+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQET4DP4CGLG","created_at":"2026-07-05T05:22:31.077027+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQET4DP4CGLGSH5H","created_at":"2026-07-05T05:22:31.077027+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQET4DP4","created_at":"2026-07-05T05:22:31.077027+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/BQET4DP4CGLGSH5HBGVPZA77ST","json":"https://pith.science/pith/BQET4DP4CGLGSH5HBGVPZA77ST.json","graph_json":"https://pith.science/api/pith-number/BQET4DP4CGLGSH5HBGVPZA77ST/graph.json","events_json":"https://pith.science/api/pith-number/BQET4DP4CGLGSH5HBGVPZA77ST/events.json","paper":"https://pith.science/paper/BQET4DP4"},"agent_actions":{"view_html":"https://pith.science/pith/BQET4DP4CGLGSH5HBGVPZA77ST","download_json":"https://pith.science/pith/BQET4DP4CGLGSH5HBGVPZA77ST.json","view_paper":"https://pith.science/paper/BQET4DP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13032&json=true","fetch_graph":"https://pith.science/api/pith-number/BQET4DP4CGLGSH5HBGVPZA77ST/graph.json","fetch_events":"https://pith.science/api/pith-number/BQET4DP4CGLGSH5HBGVPZA77ST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQET4DP4CGLGSH5HBGVPZA77ST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQET4DP4CGLGSH5HBGVPZA77ST/action/storage_attestation","attest_author":"https://pith.science/pith/BQET4DP4CGLGSH5HBGVPZA77ST/action/author_attestation","sign_citation":"https://pith.science/pith/BQET4DP4CGLGSH5HBGVPZA77ST/action/citation_signature","submit_replication":"https://pith.science/pith/BQET4DP4CGLGSH5HBGVPZA77ST/action/replication_record"}},"created_at":"2026-07-05T05:22:31.077027+00:00","updated_at":"2026-07-05T05:22:31.077027+00:00"}