|
|
|
|
|
|
by symmetricsaurus
3258 days ago
|
|
|
> 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. |
|
|