Relaxations of symmetry and the weighted Shapley values
Sign Up to like & getrecommendations! Published in 2019 at "Economics Letters"
DOI: 10.1016/j.econlet.2018.12.031
Abstract: Abstract We revisit Kalai and Samet’s (1987) first characterization of the class of weighted Shapley values. While keeping efficiency, additivity, and the null player property from the original characterization of the symmetric Shapley value, they… read more here.
Keywords: shapley values; relaxations symmetry; weighted shapley; symmetry weighted ... See more keywords
An approach to computing interval-valued discounted Shapley values for a class of cooperative games under interval data
Sign Up to like & getrecommendations! Published in 2018 at "International Journal of General Systems"
DOI: 10.1080/03081079.2018.1523903
Abstract: ABSTRACT Through adding a discounted factor, Shapley values of cooperative games are extended to interval-valued (IV) cooperative games. The main purpose of this paper is to propose the concept of IV discounted Shapley values and… read more here.
Keywords: cooperative games; class cooperative; values class; interval valued ... See more keywords
Shapley Values for Feature Selection: The Good, the Bad, and the Axioms
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Access"
DOI: 10.1109/access.2021.3119110
Abstract: The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four “favourable and fair” axioms for attribution in transferable utility games. The… read more here.
Keywords: shapley values; shapley value; feature selection; value ... See more keywords
Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning With Shapley Values
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Computational Intelligence Magazine"
DOI: 10.1109/mci.2021.3129959
Abstract: While Explainable Artificial Intelligence (XAI) is increasingly expanding more areas of application, little has been applied to make deep Reinforcement Learning (RL) more comprehensible. As RL becomes ubiquitous and used in critical and general public… read more here.
Keywords: shapley values; cooperative strategies; contribution; reinforcement learning ... See more keywords