Dec 21, 2016

Meta- reinforcement learning could prove to be such breakthrough, see [1],[2]. Also next generation ASIC accelerators (Google's TPU, Nervana) can give 10x increase in NN performance over a GPU manufactured on the same process, with another 10x possible with some form of binarized weights, e.g. BNN, XNOR-net. There are also interesting techniques to update the model's parameters in a sparse manner.

So, there certainly is a lot of room left for performance improvements!

1. 2.

Dec 07, 2016

Actually, googling 'learning to reinforcement learn' links to this paper -

Dec 05, 2016

Looks like the "UNREAL" (, "Learning to reinforcement learn" ( and "RL^2" ( are state of art in pure RL for now.

Finally there is a trend of using recurrent neural network as a top component of the Q-network. Perhaps we will see even more sophisticated RNNs like DNC and Recurrent Entity Networks applied here. Also we'll see meta-reinforcement learning applied to a curriculum of environments.