本頁只刊出中文翻譯與中文說明；英文原文請見下方原文連結。
原文連結
論文資訊
- 類型：已發表論文
- 日期：2021
摘要
An embodied 智能體, that performs a goal-directed action, influences its environment and gets influenced by it. Hence 資訊 flows not only among the 智能體s control mechanisms, but also between the 智能體 and its environment. In this article we combine different methods in order to create a framework in which we are able to closely examine the 資訊 flow among the body, 大腦 and environment of an 智能體. We test this framework in a simple experimental setup. There the 智能體s do not learn to perform a task, but we calculate the optimal behavior using the method Planning as Inference, in which the 資訊 geometric em-algorithm is used to optimize the likelihood of the goal. Then we analyze the resulting distribution using in- formation theoretic methods including measures corresponding to the concepts of Morphologica
※ 此為已發表論文，全文需透過期刊付費取得