Toward a Model of Intelligence as an Economy of Agents
Toward a Model of Intelligence as an Economy of Agents
复制标题
迈向智能体经济模型
DOI：
10.1023/a:1007593124513
复制
发表时间：
1999
期刊：
影响因子：
7.5
通讯作者：
E. Baum
中科院分区：
文献类型：
--
作者：
E. Baum
提出了一种基于市场的算法，该算法能够自主地将复杂的任务分配给多个合作的Agent，使每个Agent都有提高整个系统性能的动力。一个具体的模型，称为“哈耶克机”的建议和测试模拟块世界（BW）规划问题。哈耶克学习解决比以往任何学习算法更复杂的BW问题。给定中等奖励和简单的功能，它已经学会了有效地解决任意BW问题。哈耶克机器也可以被看作是进化经济学的一个模型。
A market-based algorithm is presented which autonomously apportions complex tasks to multiple cooperating agents giving each agent the motivation of improving performance of the whole system. A specific model, called “The Hayek Machine” is proposed and tested on a simulated Blocks World (BW) planning problem. Hayek learns to solve more complex BW problems than any previous learning algorithm. Given intermediate reward and simple features, it has learned to efficiently solve arbitrary BW problems. The Hayek Machine can also be seen as a model of evolutionary economics.