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...
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: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fnbot.2019.00103/full |
Similar Items
-
A Survey of Multi-Task Deep Reinforcement Learning
by: Nelson Vithayathil Varghese, et al.
Published: (2020-08-01) -
Deep Reinforcement Learning. Studiu de caz: Deep Q-Network
by: Mihnea Horia VREJOIU
Published: (2019-09-01) -
Train Scheduling with Deep Q-Network: A Feasibility Test
by: Intaek Gong, et al.
Published: (2020-11-01) -
CPSS LR-DDoS Detection and Defense in Edge Computing Utilizing DCNN Q-Learning
by: Zengguang Liu, et al.
Published: (2020-01-01) -
Asymptotics of Reinforcement Learning with Neural Networks
by: Sirignano, J., et al.
Published: (2022)