An implementation of Reinforcement Learning for Robot Arm of control
碩士 === 國立中正大學 === 光機電整合工程所 === 94 === In this thesis, we design a learning system for agents learning how to make the end of robot arm pointing to the goal in the work space. Our robot arm has three rollers, and one roller is viewed as an agent. We adopt a rational and convergent learning algorithm,...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2006
|
Online Access: | http://ndltd.ncl.edu.tw/handle/32809522838386191135 |