PAC Optimal Exploration Algorithm Named RMAX-KNN

PAC Optimal Exploration Algorithm Named RMAX-KNN

The balance of exploration and exploitation is one of the focuses of reinforcement learning research. The exploration helps the agent understand the environment more comprehensively and make better decisions while the exploitation helps the agent make current optimal decisions based on its current c...

Full description

Bibliographic Details
Main Author: LI Chao, MEN Changqian, WANG Wenjian
Format: Article
Language:zho
Published: Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2020-03-01
Series:Jisuanji kexue yu tansuo
Subjects:
balance of exploration and exploitation
value function
adaptive discretization of state space
probably approximately correct (pac) optimal exploration algorithm
Online Access:http://fcst.ceaj.org/CN/abstract/abstract2144.shtml

Similar Items

Similar Items