Evolution of fairness in multi-objective reinforcement learning framework
Abstract
Fairness, as a fundamental social norm, continues to pose a longstanding puzzle regarding its emergence. Traditional game-theoretic models largely rely on the assumption of \emph{Homo economicus}, wherein individuals are purely rational and self-interested, acting solely to maximize material payoffs. Such accounts, however, overlook the multidimensional nature of human decision-making, which is often shaped also by other considerations beyond economic incentives. To address this gap, we propose a multi-objective reinforcement learning framework that models the evolution of fairness as a dynamic trade-off between material payoff maximization and fairness-driven moral behavior, regulated by a fairness pressure coefficient. Using simulations of a two-objective Q-learning ultimatum game, we find that increased fairness pressure promotes fair outcomes, as expected. Strikingly, however, under moderate pressure, responder behavior reverses: responders become ``forgiving" by accepting low offers -- a pattern in line with our daily experience. Microscopic analyses reveal that this strategy reversal stems from competition between payoff-maximizing and fairness-oriented preferences. We further extend our framework to an asymmetric setting, where proposers and responders assign different weights to the two objectives. Overall, our work expands the reinforcement learning paradigm from a single-objective to a multi-objective formulation, offering a versatile tool for elucidating a broader range of human social behaviors.
Related
- TATVA: A Reinforcement Learning Framework for Quantum Circuit Synthesis
- Sustainability-Aware Discovery of Dual-Atom Hydrogen Evolution Catalysts via a Unified Machine Learning Framework for Activity and Carbon Cost
- Reinforcement learning for robust calibration of multiqudit quantum gates
- Discovering network resilience formulas with symbolized reinforcement learning
- Reinforcement learning to disentangle multiqubit quantum states from partial observations
BibTeX
@misc{zhang2026evolution,
title = {{Evolution of fairness in multi-objective reinforcement learning framework}},
author = {Jingyi Zhang and Xin Ou and Guozhong Zheng and Shengfeng Deng and Jiqiang Zhang and Li Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.34114},
eprint = {2609.34114},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.34114},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Evolution of fairness in multi-objective reinforcement learning framework
AU - Jingyi Zhang
AU - Xin Ou
AU - Guozhong Zheng
AU - Shengfeng Deng
AU - Jiqiang Zhang
AU - Li Chen
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.34114
UR - https://arxiv.org/abs/2609.34114
AB - Fairness, as a fundamental social norm, continues to pose a longstanding puzzle regarding its emergence. Traditional game-theoretic models largely rely on the assumption of \emph{Homo economicus}, wherein individuals are purely rational and self-interested, acting solely to maximize material payoffs. Such accounts, however, overlook the multidimensional nature of human decision-making, which is often shaped also by other considerations beyond economic incentives. To address this gap, we propose a multi-objective reinforcement learning framework that models the evolution of fairness as a dynamic trade-off between material payoff maximization and fairness-driven moral behavior, regulated by a fairness pressure coefficient. Using simulations of a two-objective Q-learning ultimatum game, we find that increased fairness pressure promotes fair outcomes, as expected. Strikingly, however, under moderate pressure, responder behavior reverses: responders become ``forgiving" by accepting low offers -- a pattern in line with our daily experience. Microscopic analyses reveal that this strategy reversal stems from competition between payoff-maximizing and fairness-oriented preferences. We further extend our framework to an asymmetric setting, where proposers and responders assign different weights to the two objectives. Overall, our work expands the reinforcement learning paradigm from a single-objective to a multi-objective formulation, offering a versatile tool for elucidating a broader range of human social behaviors.
ER -