Investigates reinforcement learning under partial observability and stochastic payoff matrices. Formulates coupled estimator-actor convergence guarantees for competitive and cooperative multi-agent equilibrium discovery.
@mastersthesis{sajjadi2014thesis,
title = {Simultaneous State Estimation and Reinforcement Learning in Stochastic Matrix Games},
author = {Sajjadi Mohammadabadi, Seyed Mahmoud},
school = {University of Tehran},
year = {2014}
}