EUVIMEDEUVIMED entdecken
Crossref

Fairness Aware Reinforcement Learning via Proximal Policy Optimization

Gabriele La Malfa, Jie M. Zhang, Michael Luck, Elizabeth Black

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (27) · 22725-22733

DOI: 10.1609/aaai.v40i27.39434 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Gabriele La Malfa und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fairness in multi-agent systems (MAS) focuses on equitable reward distribution among agents in scenarios involving sensitive attributes such as race, gender, or socioeconomic status. This paper introduces fairness in Proximal Policy Optimization (PPO) with a penalty term derived from a fairness definition such as demographic parity, counterfactual fairness, or conditional statistical parity. The proposed method, which we call Fair-PPO, balances reward maximisation with fairness by integrating two penalty components: a retrospective component that minimises disparities in past outcomes and a prospective component that ensures fairness in future decision-making. We evaluate our approach in two games: the Allelopathic Harvest, a cooperative and competitive MAS focused on resource collection, where some agents possess a sensitive attribute, and HospitalSim, a hospital simulation, in which agents coordinate the operations of hospital patients with different mobility and priority needs. Experiments show that Fair-PPO achieves fairer policies than PPO across the fairness metrics and, through the retrospective and prospective penalty components, reveals a wide spectrum of strategies to improve fairness; at the same time, its performance pairs with that of state-of-the-art fair reinforcement-learning algorithms. Fairness comes at the cost of reduced efficiency, but does not compromise equality among the overall population (Gini index). These findings underscore the potential of Fair-PPO to address fairness challenges in MAS.

Zitieren

APA

Malfa, G. L., Zhang, J. M., Luck, M., & Black, E. (2026). Fairness Aware Reinforcement Learning via Proximal Policy Optimization. Proceedings of the AAAI Conference on Artificial Intelligence, 40(27), 22725-22733. https://doi.org/10.1609/aaai.v40i27.39434

Vancouver

Malfa GL, Zhang JM, Luck M, Black E. Fairness Aware Reinforcement Learning via Proximal Policy Optimization. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(27):22725-22733. doi:10.1609/aaai.v40i27.39434

BibTeX
@article{Malfa2026,
  author = {Malfa, Gabriele La and Zhang, Jie M. and Luck, Michael and Black, Elizabeth},
  title = {Fairness Aware Reinforcement Learning via Proximal Policy Optimization},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {27},
  pages = {22725--22733},
  doi = {10.1609/aaai.v40i27.39434}
}
Kostenlos starten →