[bomdo]

I was a little surprised at the headline, since I expected 'outperforms' to mean that it had better end-results, which is of course not the case. GP is just much faster due to it's relative simplicity and the results are close enough to those achieved with NN and deep learning.

> Finally, while generally matching the skill level of controllers from neuro-evolution/deep learning, the genetic programming solutions evolved here are several orders of magnitude simpler, resulting in real-time operation at a fraction of the cost.

> Moreover, TPG solutions are particularly elegant, thus supporting real-time operation without specialized hardware

This is the key takeaway and yet another reminder to not make deep learning the hammer for all your fuzzy problems.

[symmetricsaurus]

> I was a little surprised at the headline, since I expected 'outperforms' to mean that it had better end-results, which is of course not the case. GP is just much faster due to it's relative simplicity and the results are close enough to those achieved with NN and deep learning.

From figure 3 in the paper it seems like it outperforms DQN on all games but one. So, it has better end results as well.

Edit: There are other results linked in this thread that are better than the 2015 DQN results that the paper refers to.