arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.04852cs.AI
收藏

平衡社会表征中的效用与认知成本

Balancing utility and cognitive cost in social representation

School of Informatics(信息学院);University of Edinburgh(爱丁堡大学)

Max Taylor-Davies, Christopher G. Lucas

AI总结:

本文针对智能体如何表征其他智能体的问题,提出在下游任务效用与信息认知成本之间取得最优平衡,并以选择性社会学习为例给出两种资源受限方法。

摘要:

为了在其环境中成功行动,智能体必须构建并维护它所遇到的其他智能体的表征。此类表征对许多任务都有用,但并非没有成本。因此,智能体必须决定选择存储多少关于其环境中智能体的信息。我们以选择性社会学习作为示例任务,引出寻找在下游效用与信息成本之间实现最优权衡的智能体表征这一问题,并说明两种资源受限社会表征的示例方法。

英文摘要:

To successfully navigate its environment, an agent must construct and maintain representations of the other agents that it encounters. Such representations are useful for many tasks, but they are not without cost. As a result, agents must make decisions regarding how much information they choose to store about the agents in their environment. Using selective social learning as an example task, we motivate the problem of finding agent representations that optimally trade off between downstream utility and information cost, and illustrate two example approaches to resource-constrained social representation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑