Login / Signup
Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion.
Jacob Buckman
Danijar Hafner
George Tucker
Eugene Brevdo
Honglak Lee
Published in:
NeurIPS (2018)
Keyphrases
</>
reinforcement learning
monte carlo
direct policy search
neural network
ensemble methods
learning algorithm
pruning algorithm
state space
function approximation
optimal policy
control policies
stochastic model
markov decision processes
prediction accuracy
training set
decision trees
feature selection
data mining