Learning Global Equilibria in Non-Concave Prospect Theoretic Games
Ashok Krishnan K. S., Lilou Malfoy, Helene Le Cadre, Ana Busic
Abstract
Human agents in non cooperative games often exhibit non rational behaviour. Prospect theory provides a behavioural framework to capture how agents perceive gains and losses under risk, but, its incorporation into games typically leads to non concave and non convex utility functions, making equilibrium computation challenging. In such cases, it is difficult to obtain algorithms that have global convergence behaviour. This paper proposes a learning algorithm which uses minorization-maximization (MM). Under a proximal Polyak-Lojasiewicz (PL) condition on the potential function, we establish global convergence of the algorithm to a potential-maximizing Nash equilibrium. We further show how the structure of the MM minorizer can be used to enable a distributed implementation of the algorithm. With additional noise injection, the individual updates of the agents can be obscured, while still ensuring global convergence.
Create a lesson
Related papers
Path-Independent Deleveraging Rules
Christoph Schlegel, Akaki Mamageishvili
Sequential Contract Design for Budgeted Crowdsourcing
Michal Feldman, Vasilis Gkatzelis, Shaul Rosner et al.
Safe Subgame Resolving in Multiplayer Games
Boning Li, Longbo Huang
Closing Gaps in Temporal Fair Division for Chores
Nicholas Teh
Uniqueness, Proximity, and Scaling in Atomic Splittable Polymatroid Congestion Games
Tobias Harks
Distortion in Online Voting
MohammadHossein Ghasemi, Masoud Seddighin, Saeed Seddighin