Please use this identifier to cite or link to this item:
Title: SCALES: From Fairness Principles to Constrained Decision-Making
Authors: Balakrishnan, Sreejith 
Bi, Jianxin
Soh, Harold 
Keywords: Fairness
Constrained Reinforcement Learning
Issue Date: 26-Jul-2022
Publisher: ACM
Citation: Balakrishnan, Sreejith, Bi, Jianxin, Soh, Harold (2022-07-26). SCALES: From Fairness Principles to Constrained Decision-Making. AIES '22: AAAI/ACM Conference on AI, Ethics, and Society. ScholarBank@NUS Repository.
Abstract: This paper proposes SCALES, a general framework that translates well-established fairness principles into a common representation based on the Constraint Markov Decision Process (CMDP). With the help of causal language, our framework can place constraints on both the procedure of decision making (procedural fairness) as well as the outcomes resulting from decisions (outcome fairness). Specifically, we show that well-known fairness principles can be encoded either as a utility component, a non-causal component, or a causal component in a SCALES-CMDP. We illustrate SCALES using a set of case studies involving a simulated healthcare scenario and the real-world COMPAS dataset. Experiments demonstrate that our framework produces fair policies that embody alternative fairness principles in single-step and sequential decision-making scenarios.
Source Title: AIES '22: AAAI/ACM Conference on AI, Ethics, and Society
DOI: 10.1145/3514094.3534190
Appears in Collections:Staff Publications
Students Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
3514094.3534190.pdfPublished version1.48 MBAdobe PDF



Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.