Login / Signup
Discounted Repeated Games Having Computable Strategies with No Computable Best Response under Subgame-Perfect Equilibria.
Jakub Dargaj
Jakob Grue Simonsen
Published in:
ACM Trans. Economics and Comput. (2022)
Keyphrases
</>
repeated games
nash equilibrium
subgame perfect
incomplete information
nash equilibria
stochastic games
average reward
markov decision processes
game theory
game theoretic
cooperative
optimal policy
worst case
learning algorithm
reinforcement learning
upper bound