Re:Why I’m Remaking OpenAI Universe
by unixpickle on Monday June 26, 2017 @02:37PM
(#14639149)
In terms of "backpropagating through thousands of frames", it's not as expensive as you might think. I've used TRPO to train RNNs on games like Atari pong with thousands of frames per episode. This can be done via an algorithm that reduces the memory complexity of RNN backpropagation (these algorithms didn't exist in 2013). See for example https://arxiv.org/abs/1606.03401.
However I think this approach is bad. Machine vision is a separate problem from reinforcement learning. You shouldn't need to be able to do both well. Machine vision consumes a ton of processing power and researcher time in figuring out the hyperparameters. And all it's doing is figuring out information that's already in memory like the location of various objects and the score. It really limits what can be done. E.g. the famous atari playing AIs by deepmind were limited to no memory and only knowing the last few frames, because backpropagating through thousands of frames was too expensive.
Because of the way NNs work, it's trivial to separate out the machine vision into a separate module. So if you have a good RNN reinforcement learning system, you can easily add a machine vision learning system to it later if you need.