Fairness in Preference-based Reinforcement Learning
This addresses fairness issues in multi-objective reinforcement learning for applications requiring equitable treatment of different objectives, representing an incremental advancement.
The paper tackles fairness in multi-objective preference-based reinforcement learning by proposing FPbRL, which learns vector reward functions using welfare-based preferences and maximizes a generalized Gini welfare function. Experimental results on three environments show that FPbRL achieves both efficiency and equity in learning effective and fair policies.
In this paper, we address the issue of fairness in preference-based reinforcement learning (PbRL) in the presence of multiple objectives. The main objective is to design control policies that can optimize multiple objectives while treating each objective fairly. Toward this objective, we design a new fairness-induced preference-based reinforcement learning or FPbRL. The main idea of FPbRL is to learn vector reward functions associated with multiple objectives via new welfare-based preferences rather than reward-based preference in PbRL, coupled with policy learning via maximizing a generalized Gini welfare function. Finally, we provide experiment studies on three different environments to show that the proposed FPbRL approach can achieve both efficiency and equity for learning effective and fair policies.