Review of Model-Based Reinforcement Learning

Review of Model-Based Reinforcement Learning

Deep reinforcement learning (DRL) as an important learning paradigm in the field of machine learning, has received increasing attentions after AlphaGo defeats the human. DRL interacts with the environment by trials and errors, and obtains the optimal policy by maximizing the cumulative reward. Reinf...

Full description

Bibliographic Details
Main Author: ZHAO Tingting, KONG Le, HAN Yajie, REN Dehua, CHEN Yarui
Format: Article
Language:zho
Published: Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2020-06-01
Series:Jisuanji kexue yu tansuo
Subjects:
deep reinforcement learning (drl)
model-based reinforcement learning
state transition model
sample efficiency
Online Access:http://fcst.ceaj.org/CN/abstract/abstract2225.shtml

Internet

http://fcst.ceaj.org/CN/abstract/abstract2225.shtml

Similar Items