Login / Signup
Contraction Conditions for Average and α-Discount Optimality in Countable State Markov Games with Unbounded Rewards.
Eitan Altman
Arie Hordijk
F. M. Spieksma
Published in:
Math. Oper. Res. (1997)
Keyphrases
</>
markov decision processes
average cost
markov games
stationary policies
state space
sufficient conditions
reinforcement learning
cooperative
linear programming
finite number
long run
adaptive control
initial state
markov decision process