AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Current State of Reinforcement Learning Models
There's a large place these days in reinforcement learning for agents and you talk about this in the book to use more ecologically valid tasks. What do you see as the current state of that I mean is that close enough to ecological validity are we still super far away? And again, with the caveat that it depends on what we're trying to do right, but assuming we're Trying to build like some human like agents or something. Yeah. There's there's obviously a lot to say here so reinforcement learning has been one of the dominant paradigms within machine learning and AI research for 40 years now. It kind of grew out of an approach which was to try and solve control problems essentially