Login / Signup
Genetic multi-armed bandits: a reinforcement learning approach for discrete optimization via simulation.
Deniz Preil
Michael Krapp
Published in:
CoRR (2023)
Keyphrases
</>
discrete optimization
multi armed bandits
reinforcement learning
combinatorial optimization problems
model free
multi armed bandit
genetic algorithm
state space
learning algorithm
bandit problems
pattern recognition
upper bound
function approximation