Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewards
This work addresses fairness in autonomous systems affecting multiple users, offering a novel formulation and methods, though it builds incrementally on standard RL techniques.
The paper tackles the problem of learning fair policies in multiobjective reinforcement learning by introducing a fairness objective and analyzing both average and discounted reward settings. It provides a theoretical bound linking discounted and average rewards, adapts deep RL algorithms for fairness, and validates the approach with experiments across three domains.
As the operations of autonomous systems generally affect simultaneously several users, it is crucial that their designs account for fairness considerations. In contrast to standard (deep) reinforcement learning (RL), we investigate the problem of learning a policy that treats its users equitably. In this paper, we formulate this novel RL problem, in which an objective function, which encodes a notion of fairness that we formally define, is optimized. For this problem, we provide a theoretical discussion where we examine the case of discounted rewards and that of average rewards. During this analysis, we notably derive a new result in the standard RL setting, which is of independent interest: it states a novel bound on the approximation error with respect to the optimal average reward of that of a policy optimal for the discounted reward. Since learning with discounted rewards is generally easier, this discussion further justifies finding a fair policy for the average reward by learning a fair policy for the discounted reward. Thus, we describe how several classic deep RL algorithms can be adapted to our fair optimization problem, and we validate our approach with extensive experiments in three different domains.