Our research goal is to design an agent that can begin with low-level sensors and effectors and autonomously learn high-level representations and actions through interaction with the environment. This chapter focuses on the problem of learning representations. We present four principles for autonomous learning of representations in a developing agent, and we demonstrate how these principles can be embodied in an algorithm. In a simulated environment with realistic physics, we show that an agent can use these principles to autonomously learn useful representations and effective hierarchical actions.
CITATION STYLE
Mugan, J., & Kuipers, B. (2013). Autonomous representation learning in a developing agent. In Computational and Robotic Models of the Hierarchical Organization of Behavior (Vol. 9783642398759, pp. 63–80). Springer-Verlag Berlin Heidelberg. https://doi.org/10.1007/978-3-642-39875-9_4
Mendeley helps you to discover research relevant for your work.