Autonomous Robots, 2013, Volume 34, Issue 4, pp 327-346.
Akihiko Yamaguchi, Jun Takamatsu, Tsukasa Ogasawara.
Graduate School of Information Science, Nara Institute of Science and Technology, 8916-5 Takayama, Ikoma, Nara, 630-0192, Japan.
Reinforcement learning (RL) for robot control is an important technology for future robots since it enables us to design a robot’s behavior using the reward function. However, RL for high degree-of-freedom robot control is still an open issue. This paper proposes a discrete action space DCOB which is generated from the basis functions (BFs) given to approximate a value function. The remarkable feature is that, by reducing the number of BFs to enable the robot to learn quickly the value function, the size of DCOB is also reduced, which improves the learning speed. In addition, a method WF-DCOB is proposed to enhance the performance, where wire-fitting is utilized to search for continuous actions around each discrete action of DCOB. We apply the proposed methods to motion learning tasks of a simulated humanoid robot and a real spider robot. The experimental results demonstrate outstanding performance.
Videos and informaiton, can be found in the project’s webpage:
The implementation of the DCOB is provided in the SkyAI (http://skyai.org/ ), an open source library of reinforcement learning methods by the authors.