Abstract | ||
---|---|---|
Learning can be an effective way for robot systems to deal with dynamic environments and changing task conditions. However, popular single- robot learning algorithms based on discounted rewards, such as Q learning, do not achieve cooperation (i.e., purposeful division of labor) when applied to task-level multirobot systems. A task- level system is defined as one performing a mission that is decomposed into subtasks shared among robots. In this paper, we demonstrate the superiority of average-reward-based learning such as the Monte Carlo algorithm for task-level multirobot systems, and suggest an explanation for this superiority. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/ROBOT.2002.1014721 | Robotics and Automation, 2002. Proceedings. ICRA '02. IEEE International Conference |
Keywords | DocType | Volume |
monte carlo methods,learning (artificial intelligence),multi-robot systems,monte carlo algorithm,average rewards,cooperative multirobot learning,dynamic environments,robot systems,task-level multirobot systems | Conference | 2 |
Issue | ISBN | Citations |
1 | 0-7803-7272-7 | 13 |
PageRank | References | Authors |
0.82 | 3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Poj Tangamchit | 1 | 18 | 3.08 |
John Dolan | 2 | 977 | 92.41 |
Khosla, P.K. | 3 | 931 | 123.84 |