Balancing the Scales: Reinforcement Learning for Fair Classification

Leon Eshuijs, Shihan Wang, Antske Fokkens


Abstract
Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent approaches have shifted towards algorithmic methods that embed fairness into the training process. These methods steer models towards fair performance, preventing potential elimination of valuable information that arises from representation manipulation. Reinforcement Learning (RL), with its ability to learn through interaction and adjust reward functions to encourage desired behaviors, presents a promising approach in this domain. In this paper, we conduct an exploratory evaluation of RL for addressing bias in imbalanced classification by scaling the reward function. We employ the contextual multi-armed bandit framework, adapt three popular RL algorithms, and conduct an extensive empirical evaluation of their relative strengths and limitations. Through this analysis, we contribute meaningful evidence to the ongoing debate between algorithmic and representational fairness approaches.
Anthology ID:
2026.iaai-1.4
Volume:
Proceedings of the Second Workshop of Identity Aware AI
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
A Pranav, Valerio Basile, Neele Falk, David Jurgens, Gabriella Lapesa, Anne Lauscher, Soda Marem Lo
Venues:
iaai | WS
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
32–46
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-iaai-04
DOI:
10.63317/4df2efew2ftw
Bibkey:
Cite (ACL):
Leon Eshuijs, Shihan Wang, and Antske Fokkens. 2026. Balancing the Scales: Reinforcement Learning for Fair Classification. In Proceedings of the Second Workshop of Identity Aware AI, pages 32–46, Palma de Mallorca, Spain. European Language Resources Association.
Cite (Informal):
Balancing the Scales: Reinforcement Learning for Fair Classification (Eshuijs et al., iaai 2026)
Copy Citation: