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:
CoRR (2010)
Keyphrases
</>
stochastic games
average reward
markov decision processes
imperfect information
optimal policy
nash equilibria
reinforcement learning
objective function
linear programming
neural network
multi agent
dynamic programming
finite state
infinite horizon
search algorithm
average cost