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
The Integrated 資訊 Theory provides a quantitative approach to consciousness and can be applied to 神經 網絡s. An embodied 智能體 controlled by such a 網絡 influences and is being influenced by its environment. This involves, on the one hand, morphological computation within goal directed action and, on the other hand, integrated 資訊 within the controller, the 智能體’s 大腦. In this article, we combine different methods in order to examine the 資訊 flows among and within the body, the 大腦 and the environment of an 智能體. This allows us to relate various 資訊 flows to each other. We test this framework in a simple experimental setup. There, we calculate the optimal policy for goal-directed behavior based on the “planning as inference” method, in which the 資訊-geometric em-algorithm is used to optimize the likelihoo
※ 此為已發表論文，全文需透過期刊付費取得