Name
Title | ||
|---|---|---|
A Study on Designing Robot Controllers by Using Reinforcement Learning with Evolutionary State Recruitment Strategy |
Abstract | ||
|---|---|---|
Recently, much attention has been focused on utilizing reinforcement learning (RL) for designing robot controllers. However, as the state spaces of these robots become continuous and high dimensional, it results in time-consuming process. In order to adopt the RL for designing the controllers of such complicated systems, not only adaptability but also computational efficiencies should be taken into account. In this paper, we introduce an adaptive state recruitment strategy which enables a learning robot to rearrange its state space conveniently according to the task complexity and the progress of the learning. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1007/978-3-540-27835-1_19 | BIOLOGICALLY INSPIRED APPROACHES TO ADVANCED INFORMATION TECHNOLOGY |
Keywords | Field | DocType |
state space,reinforcement learning | Robot learning,Evolutionary algorithm,Evolutionary robotics,Computer science,Artificial intelligence,Robot,State space,Mobile robot,Robotics,Reinforcement learning | Conference |
Volume | ISSN | Citations |
3141 | 0302-9743 | 1 |
PageRank | References | Authors |
0.42 | 12 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Toshiyuki Kondo | 1 | 131 | 28.57 |
| Koji Ito | 2 | 24 | 7.23 |