Non-Asymptotic Pure Exploration by Solving Games.

Rémy Degenne Wouter M. Koolen Pierre Ménard

Published in: NeurIPS (2019)

Keyphrases

combinatorial optimization
video games
neural network
worst case
nash equilibrium
game tree search
weighted majority
game theory
computer games
educational games
game playing
action selection
game based learning
expected values
active exploration