Name
Abstract | ||
|---|---|---|
Q-learning is an efficient algorithm to acquire adaptive behavior of the robot without a priori knowledge of the sensor space and the task. However, there is a problem in applying the Q-learning to the task in the real world. How to construct the state space suitable for the Q-learning without the knowledge of the sensor space? In this paper, we propose Q-learning with adaptive state segmentation (QLASS). QLASS provides a method to segment the sensor space incrementally based on sensor vectors and reinforcement signals. Experimental results show that QLASS can segment the sensor space effectively to accomplish the task. Furthermore, we show the obtained state space reveals the fitness landscape. |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1109/CIRA.1997.613856 | Monterey, CA |
Keywords | Field | DocType |
adaptive behavior,adaptive state segmentation,sensor vector,real world,sensor space incrementally,state space,fitness landscape,efficient algorithm,sensor space,neural networks,learning artificial intelligence,knowledge engineering,path planning,a priori knowledge,mobile robots | Motion planning,Computer vision,Fitness landscape,Computer science,Segmentation,A priori and a posteriori,Q-learning,State space search,Artificial intelligence,State space,Mobile robot,Machine learning | Conference |
ISBN | Citations | PageRank |
0-8186-8138-1 | 9 | 0.82 |
References | Authors | |
6 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hajime Murao | 1 | 21 | 6.70 |
| Shinzo Kitamura | 2 | 21 | 5.42 |