Prospect-theoretic Q-learning

We consider a prospect theoretic version of the classical Q-learning algorithm for discounted reward Markov decision processes, wherein controller perceives distorted and noisy future reward, modeled by nonlinearity that accentuates gains under-represents losses relative to reference point. analyze asymptotic behavior scheme analyzing its limiting differential equation using theory monotone dynamical systems infer behavior. Specifically, we show convergence equilibria, establish some qualitative facts about equilibria themselves.