293: True Personalization Through Reinforcement Learning
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
The Power of Reinforcement Learning
The field of reinforcement learning, this is basically automatic. The model will adjust to its own environment. And I think that's pretty powerful. It's exactly like an optimization problem versus, in the case of supervised learning, you're basically learning whatever you're feeding your model. That's a massive thing. Some companies don't do that and mistakenly so, I've seen models deteriorate to a level from a 70 or 80% accuracy to like a 48% accuracy where it's worse than flipping a coin. You can set a goal and then the system itself will find ways, as you say, to adapt. It's a very, very powerful thing that it's adapting.
Play episode from 30:09
Transcript
