← Search

Svetlin Penkov

2 accepted papers

2019

Learning Programmatically Structured Representations with Perceptor Gradients

ICLR 2019poster

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 act…

Cited by 13SourcePDFScholar
2017

Physical symbol grounding and instance learning through demonstration and eye tracking

ICRA 2017poster

It is natural for humans to work with abstract plans which are often an intuitive and concise way to represent a task. However, high level task descriptions contain symbols and concepts which need to be grounded within the environment if the plan is to be executed by an autonomous robot. The problem…

Cited by 30SourceScholar