Login / Signup
Strategy iteration is strongly polynomial for 2-player turn-based stochastic games with a constant discount factor.
Thomas Dueholm Hansen
Peter Bro Miltersen
Uri Zwick
Published in:
ICS (2011)
Keyphrases
</>
stochastic games
average reward
markov decision processes
imperfect information
nash equilibria
long run
optimal policy
objective function
reinforcement learning
multi agent
search space
particle swarm optimization
optimal strategy