In the lectures Jeremy mentioned he has not seen any interesting results of reinforcement learning. This Google Brain research might change that. Earlier this year Google Brain made an AI called AutoML which can make other AIs through reinforcement learning. In november AutoML has created NASNet for image classification. This is how it did:
"On ImageNet image classification, NASNet achieves a prediction accuracy of 82.7% on the validation set, surpassing all previous Inception models that we built [2, 3, 4]. Additionally, NASNet performs 1.2% better than all previous published results and is on par with the best unpublished result reported on arxiv.org . "
This approach sounds promising, what do you guys think?