Information-based learning by agents in unbounded state spaces
Information-based learning by agents in unbounded state spaces
复制标题
无界状态空间中代理基于信息的学习
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Fritz Sommer
中科院分区：
文献类型：
--
作者：
Shariq Mobin;James A. Arnemann;Fritz Sommer
动物可能会使用信息驱动的规划来探索未知的环境并建立其内部模型的想法已经提出了很长一段时间。最近的工作表明，使用这一原则的代理可以有效地学习离散，有界状态空间的概率环境模型。然而，动物和机器人通常面临着无限的环境。为了解决这一更具挑战性的情况下，我们研究了基于信息的学习策略的代理在无界状态空间使用非参数贝叶斯模型。具体来说，我们证明了中国餐厅过程（CRP）模型能够解决这个问题，经验贝叶斯版本能够有效地探索有限和无限的世界，依靠很少的先验信息。
The idea that animals might use information-driven planning to explore an unknown environment and build an internal model of it has been proposed for quite some time. Recent work has demonstrated that agents using this principle can efficiently learn models of probabilistic environments with discrete, bounded state spaces. However, animals and robots are commonly confronted with unbounded environments. To address this more challenging situation, we study information-based learning strategies of agents in unbounded state spaces using non-parametric Bayesian models. Specifically, we demonstrate that the Chinese Restaurant Process (CRP) model is able to solve this problem and that an Empirical Bayes version is able to efficiently explore bounded and unbounded worlds by relying on little prior information.