The Parameterized Model Checking Problem (PMCP) is to decide whether a temporal property holds for a uniform family of systems, ¢¡ , comprised of finite, but arbitrarily many,...
— We propose a new probabilistic temporal logic iLTL which captures properties of systems whose state can be represented by probability mass functions (pmf’s). Using iLTL, we c...
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
Classical game theoretic approaches that make strong rationality assumptions have difficulty modeling human behaviour in economic games. We investigate the role of finite levels o...
Debajyoti Ray, Brooks King-Casas, P. Read Montague...
We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a mo...