Play behavior is not all'marshmallow science,' and more play can equal better health. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. Breakthroughs, discoveries, and DIY tips sent six days a week. From by Heide Island, PhD, to be published on 4/28/26 by Avery, an imprint of Penguin Publishing Group, a division of Penguin Random House, LLC. From behind a stand of frozen lupine, Patches, Crest, and Slash emerge onto the wetland. Moonshine reflects off the newly fallen snow, illuminating the predawn hour with a supernatural brightness. They halt beside a corrugated metal culvert, side by side, until Patches lurches forward and leaps onto the bank of Admirals Lake. Her landing fractures the frozen lakeshore, stamping an otter-sized divot. The two girls follow behind her, each landing with a loud crunch, leaving star-shaped bull's-eyes in the ice. The otters are out early, exploiting the cold; an icy lake makes for sluggish fish.

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.

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.