Polynomial stochastic games via sum of squares optimization.

Parikshit Shah Pablo A. Parrilo

Published in: CDC (2007)

Keyphrases

stochastic games
robust optimization
markov decision processes
nash equilibria
optimization problems
nash equilibrium
learning automata
average reward
multiagent reinforcement learning
reinforcement learning algorithms
learning algorithm
reinforcement learning
multi agent
single agent
repeated games