Game-theoretic Models of Moral and Other-Regarding Agents
This work addresses the limitations of Kantian equilibria for researchers in game theory and AI ethics, proposing more practical alternatives.
This paper investigates Kantian equilibria in finite normal form games, identifying issues such as computational intractability and high miscoordination costs. It proposes alternative, computationally tractable, other-regarding equilibria and a class of actions that bridges self-regarding and Kantian behaviors.
We investigate Kantian equilibria in finite normal form games, a class of non-Nashian, morally motivated courses of action that was recently proposed in the economics literature. We highlight a number of problems with such equilibria, including computational intractability, a high price of miscoordination, and expensive/problematic extension to general normal form games. We point out that such a proper generalization will likely involve the concept of program equilibrium. Finally we propose some general, intuitive, computationally tractable, other-regarding equilibria related to Kantian equilibria, as well as a class of courses of action that interpolates between purely self-regarding and Kantian behavior.