[visarga]

The author of the article mistook the importance of environment interactivity, considering that the learning algorithm is the key difference.

I think the distinction here should be between dataset based learning and simulator based learning. The genetic algorithms mentioned in the article rely on a dynamic environment, not a static dataset. Given the dynamic environment (which is like an infinite dataset) gradient methods can learn just as well - look at AlphaGo for example. But when the model can't experiment / try new actions and see the effects, it can't separate causes from correlations.

You can extract only so much from a dataset, the model needs a way to cause and observe external effects. The environment could be the real world, a simulated world, a game, a meta neural net optimiser (AutoML), or any domain where the model can act and influence the path of learning and the environment by its previous actions.

I'm happy to see the boom in RL and simulator based learning in the last few years. It means we are on the right track.