Google AI researchers want to teach robots tasks through self-supervised reverse engineering

http://feedproxy.google.com/~r/venturebeat/SZYF/~3/3Rd18kkyUUc/

A preprint paper published by Stanford University and Google researchers proposes an AI technique that predicts how goals were achieved, effectively learning to reverse-engineer tasks. They say it enables autonomous agents to learn through self-supervision, which some experts believe is a critical step toward truly intelligent systems.  » ….