Efficient Parallel Methods for Deep Reinforcement Learning.

Alfredo V. Clemente Humberto Nicolás Castejón Martínez Arjun Chandra

Published in: CoRR (2017)

Keyphrases

reinforcement learning
significant improvement
empirical studies
benchmark datasets
data structure
real time
machine learning
learning algorithm
search algorithm
active learning
markov decision processes
machine learning methods
qualitative and quantitative
control problems