On: OpenAI Universe

[Hydraulix989]

What is state of the art in reinforcement learning right now?

https://arxiv.org/abs/1602.01783

Is there a way to deal with "sparse" training data (state, action, reward) triples -- sparse in "state"?

[sapphireblue → Hydraulix989]

Looks like the "UNREAL" (https://arxiv.org/abs/1611.05397), "Learning to reinforcement learn" (https://arxiv.org/abs/1611.05763) and "RL^2" (https://arxiv.org/abs/1611.02779) 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.

[Hydraulix989 → sapphireblue]

The crazy thing is that these stacked model architectures are starting to become another layer of "lego blocks" so to speak.

[visarga → Hydraulix989]

That paper was 10 months ago. There have been many RL papers in the meantime, but sparsity is only a problem with respect to reward, not state or action, from what I can see.

[Hydraulix989 → visarga]

You didn't answer my question. :(