Learning-Based Task Allocation in Decentralized Multirobot Systems
This paper presents an efficient decentralized multirobot system through the use of reinforcement learning coupled with heuristics to accelerate the learning process. Our heuristic functions are not reinforcement signals, but are biases to the learning space that help accelerate the exploration process and have no effect on the robot’s knowledge. Two kinds of heuristics are used: local and global. The local heuristic is derived from the local knowledge of the robot, whereas the global heuristic is derived from the data obtained from other robots. Both heuristics can help accelerating the learning process.
KeywordsReinforcement Learning Local Knowledge Travel Salesman Problem Travel Salesman Problem Reinforcement Signal
Unable to display preview. Download preview PDF.
- 1.L. Parker (1994) Heterogeneous Multi-Robot Cooperation PhD. Thesis, Dept. of Electrical Eng. and Computer Science MIT.Google Scholar
- 2.M. Mataric (1998) Learning in Multi-Robot Systems, Technical Report, CS Dept. Brandeis University.Google Scholar
- 3.T. Balch (1998) Behavioral Diversity in Learning Robot Teams, PhD. Thesis, Computer Science Dept., Georgia Tech.Google Scholar
- 5.P. Tangamchit et al. (2000) Dynamic Task Selection: A Simple Structure for Multirobot Systems, DARS 4, Springer Verlag.Google Scholar
- 6.R.A. Brooks (1985) A Robust Layered Control System for A Mobile Robot, MIT AI-LAB Technical Report.Google Scholar
- 9.P. Stone, M. Veloso (1997) Multiagent System: A Survey from a Machine Learning Perspective, CMU CS Technical Report.Google Scholar