papers AI Learner
The Github is limit! Click to go to the new site.

Learning Programmatically Structured Representations with Perceptor Gradients

2019-05-02
Svetlin Penkov, Subramanian Ramamoorthy

Abstract

We present the perceptor gradients algorithm – a novel approach to learning symbolic representations based on the idea of decomposing an agent’s policy into i) a perceptor network extracting symbols from raw observation data and ii) a task encoding program which maps the input symbols to output actions. We show that the proposed algorithm is able to learn representations that can be directly fed into a Linear-Quadratic Regulator (LQR) or a general purpose A* planner. Our experimental results confirm that the perceptor gradients algorithm is able to efficiently learn transferable symbolic representations as well as generate new observations according to a semantically meaningful specification.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.00956

PDF

http://arxiv.org/pdf/1905.00956


Similar Posts

Comments