Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning
This work tackles the problem of achieving fairness in multi-agent reinforcement learning for systems where multiple agents cooperate, offering an incremental improvement over existing methods.
This paper addresses the challenge of learning fair policies in cooperative multi-agent reinforcement learning by optimizing a welfare function that balances efficiency and equity. The proposed neural network architecture, comprising two sub-networks, demonstrates superior performance compared to previous methods in various experimental domains.
We consider the problem of learning fair policies in (deep) cooperative multi-agent reinforcement learning (MARL). We formalize it in a principled way as the problem of optimizing a welfare function that explicitly encodes two important aspects of fairness: efficiency and equity. As a solution method, we propose a novel neural network architecture, which is composed of two sub-networks specifically designed for taking into account the two aspects of fairness. In experiments, we demonstrate the importance of the two sub-networks for fair optimization. Our overall approach is general as it can accommodate any (sub)differentiable welfare function. Therefore, it is compatible with various notions of fairness that have been proposed in the literature (e.g., lexicographic maximin, generalized Gini social welfare function, proportional fairness). Our solution method is generic and can be implemented in various MARL settings: centralized training and decentralized execution, or fully decentralized. Finally, we experimentally validate our approach in various domains and show that it can perform much better than previous methods.