Applications of asynchronous deep reinforcement learning based on dynamic updating weights.

Xingyu Zhao Shifei Ding Yuexuan An Weikuan Jia

Published in: Appl. Intell. (2019)

Keyphrases

reinforcement learning
linear combination
state space
dynamically updated
learning algorithm
content analysis
weighted average
real time
real world
information systems
objective function
function approximation
weighted sum
reinforcement learning algorithms
temporal difference learning