Action Segmentation and Learning by Inverse Reinforcement Learning

碩士 === 國立中山大學 === 電機工程學系研究所 === 104 === Reinforcement learning allows agents to learn behaviors through trial and error. However, as the level of difficulty increases, the reward function of the mission also becomes harder to be defined. By combining the concepts of Adaboost classifier and Upper C...

Full description

Bibliographic Details
Main Authors: Hsuan-yi Chiang, 江炫儀
Other Authors: Kao-Shing Hwang
Format: Others
Language:en_US
Published: 2015
Online Access:http://ndltd.ncl.edu.tw/handle/24130256006959006664