Back to Search
Start Over
Continuous-time path planning for multi-agents with fuzzy reinforcement learning.
- Source :
-
Journal of Intelligent & Fuzzy Systems . 2017, Vol. 33 Issue 1, p491-501. 11p. - Publication Year :
- 2017
-
Abstract
- There are a lot of applications of multi-agent systems, such as robot navigation, distributed control, data mining, etc. Reinforcement learning (RL) is a popular method used in multi agent path planning. RL algorithm needs an accurate representation of a small and discrete space. In order to plan multi agents in continuous time, this paper approximate the Q-values with the fuzzy logic, such that the modified RL canwork in continuous state space. The fuzzy reinforcement learning proposed in this paper uses fuzzy Q-iteration algorithm and a modified Wolf-PH algorithm. The convergence and existence of the algorithm are proven. The continuous time planning algorithm is applied to a cooperative task of two mobile Khepera robots. The experimental results show the effectiveness of the new path planning method for the multi agents in continuous time. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10641246
- Volume :
- 33
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- Journal of Intelligent & Fuzzy Systems
- Publication Type :
- Academic Journal
- Accession number :
- 123765526
- Full Text :
- https://doi.org/10.3233/JIFS-161822