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：2013
摘要
One of the main challenges in the field of embodied 人工智慧 is the open-ended autonomous learning of complex behaviors. Our approach is to use task-independent, 資訊-driven intrinsic motivation(s) to support task-dependent learning. The work presented here is a preliminary step in which we investigate the predictive 資訊 (the mutual 資訊 of the past and future of the sensor stream) as an intrinsic drive, ideally supporting any kind of task acquisition. Previous experiments have shown that the predictive 資訊 (PI) is a good candidate to support autonomous, open-ended learning of complex behaviors, because a maximization of the PI corresponds to an exploration of morphology- and environment-dependent behavioral regularities. The idea is that these regularities can then be exploited in order to solve an
※ 此為已發表論文，全文需透過期刊付費取得