Deep reinforcement learning in games does not translate to real-world AI
Dileep George · The State of AI & What's Next // Dileep George, Vicarious AI (FirstMark's Data Driven NYC) · Dec 11, 2018 · at 18:23
Dileep George, co-founder of Vicarious AI, discusses the limitations of deep learning and game benchmarks at Data Driven NYC in 2018.
0:00 / 0:13exact quote · 14.0s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“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.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Dileep George
DeepMind's reinforcement learning fails on minor visual changes while Vicarious succeeds
“So if you use, ah, if you compare, ah, Vicarious, ah, system with, ah, DeepMind system, ah, for example, if you change the brightness of the screen DeepMind system will stop playing, ah, because it will, ah, get confused, ah, and if you offset the paddle we ou…”
The delay in creating multipurpose robots is software, not hardware
“And we don't have Rosie the robot not because we haven't, you know, we haven't solved the hardware problem. It's a software problem.”
AI practitioners are shifting toward models inspired by neuroscience and cognitive science
“The mood is starting to shift in the field especially the practitioners that are close to the problem. They understand that, okay, the current wave of excitement has its limitations, and we need to look more deeply at the problems and import insights from neur…”
Embedding assumptions about object interactions enables AI models to generalize better
“Our, what we are doing differently compared to what was attempted previously was that we are putting more assumptions into our model in the sense of that there are objects in the world. There are interactions between objects, et cetera. Those assumptions are f…”
Intelligence is the ability to model the world and act upon it
“Intelligence is the ability to model the world and to act purposefully on it.”
Deep neural networks are easily fooled by abstract adversarial visual patterns
“In fact even our sophisticated deep neural networks can be fooled very easily by showing creating these weird-looking patterns, and those patterns will get interpreted with very high confidence as, you know, things like starfish, freight car, remote control et…”