Name
Abstract | ||
|---|---|---|
As a novel learning method, reinforced learning by which a robot acquires control rules through trial and error has gotten a lot of attention. However, it is quite difficult for robots to acquire control rules by reinforcement learning in real space because many learning trials are needed to achieve the control rules; the robot itself may lose control, or there may be safety problems with the control objects. In this paper, we propose a method in which a robot in real space learns a virtual task; then the task is transferred from virtual to real space. The robot eventually acquires the task in a real environment. We show that a real robot can acquire a task in virtual space with an input device by an example of an inverted pendulum. Next, we verify availability that the acquired task in virtual space can be applied to a real world task. We emphasize the utilization of virtual space to effectively obtain the real world task. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/978-3-540-69162-4_26 | ICONIP |
Keywords | Field | DocType |
virtual space,real space,virtual task,real robot,task learning,control rule,virtual environment,real world task,control object,learning trial,acquired task,real environment,reinforcement learning,input device,inverted pendulum | Robot learning,Trial and error,Inverted pendulum,Virtual machine,Computer science,Artificial intelligence,Robot,Machine learning,Reinforcement learning,Input device,Instructional simulation | Conference |
Volume | ISSN | Citations |
4985 | 0302-9743 | 1 |
PageRank | References | Authors |
0.36 | 11 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tadashi Tsubone | 1 | 20 | 9.43 |
| Ken-ichi Kurimoto | 2 | 4 | 1.05 |
| Koichi Sugiyama | 3 | 1 | 0.69 |
| Yasuhiro Wada | 4 | 225 | 62.58 |