{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PM4FTMNRLMLU7FTJ5EXXDZNCJI","short_pith_number":"pith:PM4FTMNR","schema_version":"1.0","canonical_sha256":"7b3859b1b15b174f9669e92f71e5a24a033f246a84f9493793305a06375042d9","source":{"kind":"arxiv","id":"2212.01382","version":5},"attestation_state":"computed","paper":{"title":"Welfare and Fairness in Multi-objective Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"Brandon Fain, Muhang Tian, Nianli Peng, Zimeng Fan","submitted_at":"2022-11-30T01:40:59Z","abstract_excerpt":"We study fair multi-objective reinforcement learning in which an agent must learn a policy that simultaneously achieves high reward on multiple dimensions of a vector-valued reward. Motivated by the fair resource allocation literature, we model this as an expected welfare maximization problem, for some nonlinear fair welfare function of the vector of long-term cumulative rewards. One canonical example of such a function is the Nash Social Welfare, or geometric mean, the log transform of which is also known as the Proportional Fairness objective. We show that even approximately optimal optimiza"},"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":"2212.01382","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-11-30T01:40:59Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"92a0b64aaa7ff7ce278594a98044e2f8e957bf0a43ace479eaac63775261b7bb","abstract_canon_sha256":"4035b0064305cd1bffa509e748d5e17c480faddc11bf0168a5af9b1ccc0546c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:38.464444Z","signature_b64":"8ADpA0GzlKkGBaSGVGdxLy77uGqbRig2aCzv+KqdBkXUWj/bjtzp/CVw0WjK14WH13OVJG/NbuyuzXw24sVuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b3859b1b15b174f9669e92f71e5a24a033f246a84f9493793305a06375042d9","last_reissued_at":"2026-07-05T07:42:38.464018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:38.464018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Welfare and Fairness in Multi-objective Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"Brandon Fain, Muhang Tian, Nianli Peng, Zimeng Fan","submitted_at":"2022-11-30T01:40:59Z","abstract_excerpt":"We study fair multi-objective reinforcement learning in which an agent must learn a policy that simultaneously achieves high reward on multiple dimensions of a vector-valued reward. Motivated by the fair resource allocation literature, we model this as an expected welfare maximization problem, for some nonlinear fair welfare function of the vector of long-term cumulative rewards. One canonical example of such a function is the Nash Social Welfare, or geometric mean, the log transform of which is also known as the Proportional Fairness objective. We show that even approximately optimal optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01382","kind":"arxiv","version":5},"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/2212.01382/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":"2212.01382","created_at":"2026-07-05T07:42:38.464076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.01382v5","created_at":"2026-07-05T07:42:38.464076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01382","created_at":"2026-07-05T07:42:38.464076+00:00"},{"alias_kind":"pith_short_12","alias_value":"PM4FTMNRLMLU","created_at":"2026-07-05T07:42:38.464076+00:00"},{"alias_kind":"pith_short_16","alias_value":"PM4FTMNRLMLU7FTJ","created_at":"2026-07-05T07:42:38.464076+00:00"},{"alias_kind":"pith_short_8","alias_value":"PM4FTMNR","created_at":"2026-07-05T07:42:38.464076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18111","citing_title":"Learning Fair Pareto-Optimal Policies in Multi-Objective Reinforcement Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01961","citing_title":"Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI","json":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI.json","graph_json":"https://pith.science/api/pith-number/PM4FTMNRLMLU7FTJ5EXXDZNCJI/graph.json","events_json":"https://pith.science/api/pith-number/PM4FTMNRLMLU7FTJ5EXXDZNCJI/events.json","paper":"https://pith.science/paper/PM4FTMNR"},"agent_actions":{"view_html":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI","download_json":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI.json","view_paper":"https://pith.science/paper/PM4FTMNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.01382&json=true","fetch_graph":"https://pith.science/api/pith-number/PM4FTMNRLMLU7FTJ5EXXDZNCJI/graph.json","fetch_events":"https://pith.science/api/pith-number/PM4FTMNRLMLU7FTJ5EXXDZNCJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/action/storage_attestation","attest_author":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/action/author_attestation","sign_citation":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/action/citation_signature","submit_replication":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/action/replication_record"}},"created_at":"2026-07-05T07:42:38.464076+00:00","updated_at":"2026-07-05T07:42:38.464076+00:00"}