Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning

Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning

A deep Q network (DQN) (Mnih et al., 2013) is an extension of Q learning, which is a typical deep reinforcement learning method. In DQN, a Q function expresses all action values under all states, and it is approximated using a convolutional neural network. Using the approximated Q function, an optim...

Full description

Bibliographic Details
Main Authors: Shota Ohnishi, Eiji Uchibe, Yotaro Yamaguchi, Kosuke Nakanishi, Yuji Yasui, Shin Ishii
Format: Article
Language:English
Published: Frontiers Media S.A. 2019-12-01
Series:Frontiers in Neurorobotics
Subjects:
deep reinforcement learning
deep Q network
regularization
learning stabilization
target network
constrained reinforcement learning
Online Access:https://www.frontiersin.org/article/10.3389/fnbot.2019.00103/full

Internet

https://www.frontiersin.org/article/10.3389/fnbot.2019.00103/full

Similar Items