Exploration and Exploitation in Visuomotor Prediction of Autonomous Agents
This work addresses the challenge of autonomous learning in robotics or AI systems, but it appears incremental as it applies existing methods to a specific, simplified domain.
The paper tackles the problem of enabling autonomous agents to predict the effects of their actions on visual sensor data, using an Extreme Learning Machine for visuomotor prediction and testing various control techniques for balancing exploration and exploitation in a simple 2D greyscale image system.
This paper discusses various techniques to let an agent learn how to predict the effects of its own actions on its sensor data autonomously, and their usefulness to apply them to visual sensors. An Extreme Learning Machine is used for visuomotor prediction, while various autonomous control techniques that can aid the prediction process by balancing exploration and exploitation are discussed and tested in a simple system: a camera moving over a 2D greyscale image.