Abstract | ||
---|---|---|
Policy Learning approaches are among the best suited methods for high-dimensional, continuous control systems such as anthropomorphic robot arms and humanoid robots. In this paper, we show two contributions: firstly, we show a unified perspective which allows us to derive several policy learning algorithms from a common point of view, i.e, policy gradient algorithms, natural-gradient algorithms and EM-like policy learning. Secondly, we present several applications to both robot motor primitive learning as well as to robot control in task space. Results both from simulation and several different real robots are shown. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-89722-4_17 | EWRL |
Keywords | Field | DocType |
policy learning approach,anthropomorphic robot arm,em-like policy learning,robot control,policy gradient algorithm,common point,different real robot,humanoid robot,unified perspective,continuous control system,robot motor primitive learning,control system,robot arm | Robot learning,Robot control,Computer vision,Social robot,Computer science,Personal robot,Artificial intelligence,Mobile robot,Arm solution,Reinforcement learning,Humanoid robot | Conference |
Volume | ISSN | Citations |
5323 | 0302-9743 | 2 |
PageRank | References | Authors |
0.36 | 11 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jan Peters | 1 | 3553 | 264.28 |
jens kober | 2 | 915 | 45.54 |
duy nguyentuong | 3 | 438 | 26.22 |