Learning coordination strategies for multiple robots

Ho, F.; Kamel, Mohamed S.

doi:10.1109/iros.1998.724632

Cited by 1 publication

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Figure 3 ( (5) It should be mentioned that after every agent abstracts the sensory data and saves it as input state in its memory, in order to reduce the amount of the input states, we will shift the state matrix k M to the right or the left, if the agent has explored the same input state before. In Figure 3 for example, if we shift the input state matrix in (D) right by one step, we will get the same input state matrix as in (C) that the prey agent has already explored.…”

Section: Environment Sensing Mechanismmentioning

confidence: 99%

See 1 more Smart Citation

The study of cooperative behavior in predator-prey problem of multi-agent systems

Zhao

Jin

Proceedings Autonomous Decentralized Systems, 2005. ISADS 2005.

View full text Add to dashboard Cite

An important study in multi-agent systems is the development of cooperative behavior between agents that have a shared goal. In this paper an example of the predator-prey problem is studied in which four predator agents, using the reinforcement learning method, in an attempt to collectively achieve the task of surrounding one prey agent. First, we describe the structure of the predator agents and the prey agent with their state sensing capability, the action learning method and the action choosing mechanism. Next we study two cooperative behavior mechanisms between agents of multi-agent systems in predator-prey problem. Finally, we demonstrate that cooperative agents outperform agents without cooperative behavior according to simulations of the predator-prey problem and display the corresponding experimental results. 0-7803-8963-8/05/$20.00 ©2005 IEEE.

show abstract

Section: Environment Sensing Mechanismmentioning

confidence: 99%

“…A variety of studies have been proposed [2], [3], [4], [5]. Tan [2] uses a Q-learning algorithm for predator-prey problem in a two-dimensional grid world which demonstrates that reinforcement learning agents can learn cooperative behavior and the effectiveness of cooperation in a predator-prey problem.…”

Section: Introductionmentioning

confidence: 99%

The study of cooperative behavior in predator-prey problem of multi-agent systems

Zhao

Jin

Proceedings Autonomous Decentralized Systems, 2005. ISADS 2005.

View full text Add to dashboard Cite

show abstract

Learning coordination strategies for multiple robots

Cited by 1 publication

References 11 publications

The study of cooperative behavior in predator-prey problem of multi-agent systems

The study of cooperative behavior in predator-prey problem of multi-agent systems

Contact Info

Product

Resources

About