Login / Signup
Multi-Armed Bandits for Minesweeper: Profiting from Exploration-Exploitation Synergy.
Igor Q. Lordeiro
Douglas de O. Cardoso
Published in:
CoRR (2020)
Keyphrases
</>
bandit problems
exploration exploitation
multi armed bandits
decision problems
learning algorithm
reinforcement learning
special case
visual information
optimal strategy
expected utility