Design Environment of Reinforcement Learning Agents for Intelligent Multiagent System
暂无分享,去创建一个
The agent-oriented computing is a technique for generating the agent who operates autonomously according to the behavior knowledge. Moreover, agent can have the characteristic called "Learningh skill. More efficient operation of agents can be expected by realizing "Learning" skill. In this research, our aim is to support agent designer who designs and develops the intelligent agent system equipped with gLearningh skill. We propose design environment of reinforcement learning agents on repository-based agent framework called DASH framework. Proposed mechanism enables agent designer to design and implement the learning agents without highly expertise, therefore we can reduce the designer's burden. In this paper, we explain the DASH framework, Profit Sharing and proposed design support mechanism. Moreover we show the effectiveness of the proposal method through the some experiments.
[1] J. Grefenstette. Credit Assignment in Rule Discovery Systems Based on Genetic Algorithms , 2005, Machine Learning.
[2] K. Sugawara. Flexible Distributed Agent System programmed by a Rule-based Language , 2002 .
[3] Agostino Poggi,et al. Jade - a fipa-compliant agent framework , 1999 .