Model Free Versus Model Based?

Reinforcement learning is this approach where you integrate the information of about reward you've received for a given choice over time, and you summarize it into a single cash value. So like if I go to this restaurant, in average, it has an expected value of point eight, this one point six or something like that. It's obviously super popular framework, more basis small free and it's resonates a lot with the whole thinking fast and thinking slow,. There's a whole like history of psychology around dual systems like this, and everybody likes it.

Transcript

Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.