Title :
Reinforcement learning approach to motion control of 2-link planer manipulator with a free joint
Author :
Goto, Takakuni ; Kamaya, Hiroyuki ; Abe, Kenichi
Author_Institution :
Dept. of Elec. & Comm. Eng., Tohoku Univ., Sendai, Japan
Abstract :
In this paper, reinforcement learning approach to motion control of 2-link planer underactuated manipulator is described. This manipulator has one passive joint and is difficult to control. The experiments of learning to control this manipulator by RL and human are executed. Using the experimental results, the associations between RL and human learning are considered.
Keywords :
learning (artificial intelligence); manipulators; motion control; 2-link planer underactuated manipulator; free joint; human learning; manipulator control; manual control; motion control; passive joint; reinforcement learning;
Conference_Titel :
SICE 2004 Annual Conference
Conference_Location :
Sapporo
Print_ISBN :
4-907764-22-7