Deep Reinforcement Learning
topic on 6 shows · 9 statements across 7 episodes
We Live to Build 
Latent Space 
Invest Like the Best 
Capital Allocators 
the MAD Podcast 
the a16z Podcast
9 statements about Deep Reinforcement Learning, every show
Levine: Deep RL Is Essential for Robots to Exceed Human Performance
“I think that the first deep reinforcement learning systems, which were in the early 20 tens, like those are probably a milestone because deep reinforcement learning gives us a way to go beyond human level performance, which I think will be essential for roboti…”
Eysenbach: Historically, 'deep' RL meant only two to four layers
“So it's like, probably my lab works on deep reinforcement learning, but historically deep meant like two or three or four layers.”
Dubois: Industrial reinforcement learning cannot generalize across factory tasks
“And that's really interesting because it learns to build long-term strategy. It can make decisions and things like that, but it's still so narrow. Like it's really capable, but only on the task that it's been trained on. Like if you even just put it on a diffe…”
Bonafede: Rosetta Analytics uses deep reinforcement learning for portfolio optimization
“So in our case, we use neural networks to make a directional prediction, but we have actually taken the neural network and we're using a concept called deep reinforcement learning, which is, you can think of it as a decision framework, but an optimization that…”
Bonafede: Deep reinforcement learning discovers relationships traditional optimizers miss
“But in a deep reinforcement learning process, you're using that neural network, and it has the ability to learn new relationships where all other optimization functions will only use the parameters or the factors or the framework that the model itself is capab…”
Spisak: Domain transfer from simulation for autonomous driving remains unsolved
“When you talk about having RRL applied in say like autonomous driving, having a car drive around and learn how to drive, you know, by crashing a million times isn't tractable as a, you know, as an algorithm. So it's, you know, being able to do all that simulat…”
Deep reinforcement learning in games does not translate to real-world AI
“But those excitements Turned, turned out to be premature because it's, yeah, game playing is an easier problem compared to real world problems. Those techniques do not translate to real world problems.”
Marcus: AI has made little progress toward strategic general game players
“There's still been very little progress in building a general game player that can play games that require strategy or insight, complex three-dimensional graphics.”