Approximate Predictive Representations of Partially Observable Systems
Monica Dinculescu, Doina Precup · 2010
We provide a novel view of learning an approximate model of a partially observable environment from data and present a simple implementation of the idea. The learned model abstracts away unnecessary details of the agent’s experience and focuses only on making certain predictions of interest. We illustrate our approach in small computational examples, demonstrating the data efficiency of the algorithm. 1.