Completely mixed strategies for single controller unichain semi-Markov games with undiscounted payoffs.

Prasenjit Mondal

Published in: Oper. Res. (2018)

Keyphrases

markov games
markov decision processes
finite state
initial state
markov decision process
average cost
control system
multiagent reinforcement learning
stochastic games
control algorithm
repeated games
reinforcement learning
closed loop
monte carlo
optimal policy
markov chain
mobile robot
optimal solution