Login / Signup
Learning Exploration/Exploitation Strategies for Single Trajectory Reinforcement Learning.
Michael Castronovo
Francis Maes
Raphael Fonteneau
Damien Ernst
Published in:
EWRL (2012)
Keyphrases
</>
reinforcement learning
exploration exploitation
learning process
learning algorithm
active learning
supervised learning
state space
learning environment
markov decision processes
action selection
learning agents
bandit problems