Stephen Downes

As the teaser says, "Come for the reinforcement learning, stay for the GIFs." Stay for the short video, actually, to watch a human-shaped robot figure navigate complex landscapes. This aerticle summarizes the outcomes of a reserach paper (14 page PDF), It wasn't given instructions on how to do this; it learned how to jump and climb via reinforcement learning. "It's clear that DeepMind is using creative solutions to get around the obstacles it's presented with; much of the time, the movement that provides the most efficient solution isn't exactly natural looking."