Reducing Trials by Thinning-Out in Skill Discovery

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.

• Type: Conference
• Year: 2007
• Where: DIS
• Authors: Hayato Kobayashi, Kohei Hatano, Akira Ishino, Ayumi Shinohara
• Keywords: DIS 2007, Skill Discovery, Sophisticated Motions, Theoretical Computer Science, Thinning-out Means