{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BB7GSO3IJQJ542LW57PWV56PVX","short_pith_number":"pith:BB7GSO3I","schema_version":"1.0","canonical_sha256":"087e693b684c13de6976efdf6af7cfadc0fd7d06db268a1ca6b203b7800201a6","source":{"kind":"arxiv","id":"2205.10032","version":1},"attestation_state":"computed","paper":{"title":"Survey on Fair Reinforcement Learning: Theory and Practice","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akrati Saxena, George Fletcher, Maryam Tavakol, Mykola Pechenizkiy, Pratik Gajane","submitted_at":"2022-05-20T09:07:28Z","abstract_excerpt":"Fairness-aware learning aims at satisfying various fairness constraints in addition to the usual performance criteria via data-driven machine learning techniques. Most of the research in fairness-aware learning employs the setting of fair-supervised learning. However, many dynamic real-world applications can be better modeled using sequential decision-making problems and fair reinforcement learning provides a more suitable alternative for addressing these problems. In this article, we provide an extensive overview of fairness approaches that have been implemented via a reinforcement learning ("},"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":"2205.10032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-20T09:07:28Z","cross_cats_sorted":[],"title_canon_sha256":"84d7d0d2da53d6dfca35dbaedaa6897a83747e59d0a0daa85c9570f09532e4a5","abstract_canon_sha256":"d0ae476fc67d47bdaf8f5f538c9a6941daabea167d16422dad9d9a1b3efef331"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:02.689415Z","signature_b64":"YcZSXMqsoJ/6Sb4ARnUCPcwNJSR5gfFH65YNmD8MjLyr+VHYKqaf2YS/ld88HX3zGpzv8y7PLO32SoQCBf5NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"087e693b684c13de6976efdf6af7cfadc0fd7d06db268a1ca6b203b7800201a6","last_reissued_at":"2026-07-05T04:25:02.688850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:02.688850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Survey on Fair Reinforcement Learning: Theory and Practice","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akrati Saxena, George Fletcher, Maryam Tavakol, Mykola Pechenizkiy, Pratik Gajane","submitted_at":"2022-05-20T09:07:28Z","abstract_excerpt":"Fairness-aware learning aims at satisfying various fairness constraints in addition to the usual performance criteria via data-driven machine learning techniques. Most of the research in fairness-aware learning employs the setting of fair-supervised learning. However, many dynamic real-world applications can be better modeled using sequential decision-making problems and fair reinforcement learning provides a more suitable alternative for addressing these problems. In this article, we provide an extensive overview of fairness approaches that have been implemented via a reinforcement learning ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10032","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.10032/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":"2205.10032","created_at":"2026-07-05T04:25:02.688943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.10032v1","created_at":"2026-07-05T04:25:02.688943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10032","created_at":"2026-07-05T04:25:02.688943+00:00"},{"alias_kind":"pith_short_12","alias_value":"BB7GSO3IJQJ5","created_at":"2026-07-05T04:25:02.688943+00:00"},{"alias_kind":"pith_short_16","alias_value":"BB7GSO3IJQJ542LW","created_at":"2026-07-05T04:25:02.688943+00:00"},{"alias_kind":"pith_short_8","alias_value":"BB7GSO3I","created_at":"2026-07-05T04:25:02.688943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06443","citing_title":"The Fair Game: Auditing & Debiasing AI Algorithms Over Time","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BB7GSO3IJQJ542LW57PWV56PVX","json":"https://pith.science/pith/BB7GSO3IJQJ542LW57PWV56PVX.json","graph_json":"https://pith.science/api/pith-number/BB7GSO3IJQJ542LW57PWV56PVX/graph.json","events_json":"https://pith.science/api/pith-number/BB7GSO3IJQJ542LW57PWV56PVX/events.json","paper":"https://pith.science/paper/BB7GSO3I"},"agent_actions":{"view_html":"https://pith.science/pith/BB7GSO3IJQJ542LW57PWV56PVX","download_json":"https://pith.science/pith/BB7GSO3IJQJ542LW57PWV56PVX.json","view_paper":"https://pith.science/paper/BB7GSO3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.10032&json=true","fetch_graph":"https://pith.science/api/pith-number/BB7GSO3IJQJ542LW57PWV56PVX/graph.json","fetch_events":"https://pith.science/api/pith-number/BB7GSO3IJQJ542LW57PWV56PVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BB7GSO3IJQJ542LW57PWV56PVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BB7GSO3IJQJ542LW57PWV56PVX/action/storage_attestation","attest_author":"https://pith.science/pith/BB7GSO3IJQJ542LW57PWV56PVX/action/author_attestation","sign_citation":"https://pith.science/pith/BB7GSO3IJQJ542LW57PWV56PVX/action/citation_signature","submit_replication":"https://pith.science/pith/BB7GSO3IJQJ542LW57PWV56PVX/action/replication_record"}},"created_at":"2026-07-05T04:25:02.688943+00:00","updated_at":"2026-07-05T04:25:02.688943+00:00"}