Deep RL Doesn’t Work Yet!

Deep reinforcement learning is surrounded by mountains and mountains of hype. And for good reasons! Reinforcement learning is an incredibly general paradigm, and in principle, a robust and performant RL system should be great at everything. Merging this paradigm with the empirical power of deep learning is an obvious fit. Deep RL is one of the closest things that looks anything like AGI, and that’s the kind of dream that fuels billions of dollars of funding. Unfortunately, it doesn’t really work yet. Discussion of this article by Alex Irpan Please watch this if you are considering an RL project! Note this is an out-take from a ML Street Talk episode on Microsof Bonsai
Back to Top