Approximate exploitability: Learning a best response in large games.

Finbarr Timbers Edward Lockhart Martin Schmid Marc Lanctot Michael Bowling

Published in: CoRR (2020)

Keyphrases

learning process
reinforcement learning
learning algorithm
online learning
mobile learning
e learning
prior knowledge
learning analytics
supervised learning
knowledge acquisition
unsupervised learning
learning systems
language learning
inductive inference
stochastic games
learning agents