A DQN-Based Reinforcement Learning Model for Neural Network Architecture Search
碩士 === 國立中央大學 === 資訊管理學系 === 107 === Designing neural network (NN) architectures requires both human expertise and labor. New architectures are handcrafted by careful experimentation or modified from a handful of existing networks. We introduce HCM, a meta-modeling algorithm based on reinforcement l...
Main Authors: | Tzu-Han Tsai, 蔡子涵 |
---|---|
Other Authors: | Yi-Cheng Chen |
Format: | Others |
Language: | en_US |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/qf2jk4 |
Similar Items
-
Multi-robot path planning based on a deep reinforcement learning DQN algorithm
by: Yang Yang, et al.
Published: (2020-06-01) -
DQN Tackling the Game of Candy Crush Friends Saga : A Reinforcement Learning Approach
by: Karnsund, Alice
Published: (2019) -
A Policy-Based Reinforcement Learning Model for Neural Network Architecture Search
by: Chung-Ting Hsiao, et al.
Published: (2019) -
Path Planning via an Improved DQN-Based Learning Policy
by: Liangheng Lv, et al.
Published: (2019-01-01) -
Flexible Transmission Network Expansion Planning Based on DQN Algorithm
by: Yuhong Wang, et al.
Published: (2021-04-01)