Login / Signup
Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits & Dueling Bandits.
Arnab Maiti
Ross Boczar
Kevin G. Jamieson
Lillian J. Ratliff
Published in:
AISTATS (2024)
Keyphrases
</>
stochastic systems
stochastic models
multi armed bandit
multi armed bandits
regret bounds
singular value decomposition
online learning
game design
stochastic processes
linear algebra
data sets
video games
cost sensitive
singular values
hopfield neural network
matrix representation