Name
Abstract | ||
|---|---|---|
In this paper, we propose a new concept, thinning-out, for reducing the number of trials in skill discovery. Thinning-out means to skip over such trials that are unlikely to improve discovering results, in the same way as "pruning" in a search tree. We show that our thinningout technique significantly reduces the number of trials. In addition, we apply thinning-out to the discovery of good physical motions by legged robots in a simulation environment. By using thinning-out, our virtual robots can discover sophisticated motions that is much different from the initial motion in a reasonable amount of trials. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/978-3-540-75488-6_13 | Discovery Science |
Keywords | Field | DocType |
skill discovery,search tree,good physical motion,sophisticated motion,reasonable amount,legged robot,initial motion,new concept,simulation environment,thinningout technique | Thinning,Computer science,Legged robot,Artificial intelligence,Robot,Score,Machine learning,Pruning,Search tree | Conference |
Volume | ISSN | ISBN |
4755 | 0302-9743 | 3-540-75487-3 |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hayato Kobayashi | 1 | 21 | 4.69 |
| Hatano, Kohei | 2 | 88 | 21.16 |
| Akira Ishino | 3 | 54 | 7.31 |
| Ayumi Shinohara | 4 | 936 | 88.28 |