センサモータ予測による部分観測環境での表現学習
Representation Learning in Partially Observable Environments using Sensorimotor Prediction
行動中に得られるセンサモータ情報を時間的に統合し、予測に有用な感覚表現を学習するモデルを提案。単純な例で運動と記憶の役割を検証した。
著者: Thibaut Kulak, Michael Garcia Ortiz
分類: cs.AI, cs.RO
原文アブストラクト
In order to explore and act autonomously in an environment, an agent needs to learn from the sensorimotor information that is captured while acting. By extracting the regularities in this sensorimotor stream, it can learn a model of the world, which in turn can be used as a basis for action and exploration. This requires the acquisition of compact representations from a possibly high dimensional raw observation, which is noisy and ambiguous. In this paper, we learn sensory representations from sensorimotor prediction. We propose a model which integrates sensorimotor information over time, and project it in a sensory representation which is useful for prediction. We emphasize on a simple example the role of motor and memory for learning sensory representations.
