
Episode 24: Jack Parker-Holder, DeepMind, on open-endedness, evolving agents and environments, online adaptation, and offline learning
Generally Intelligent
Foundation Models for Decision Making
I think one of those in reinforcement learning, or at least actually in more broadly decision making is the foundation models on large language models. And I think they've been used really effectively for some types of vision and LP. But how we can use these kind of models in reinforcement learning or decision making more broadly is not clear at all. These are just kind of initial directions, but they've all arise in the last year or two due to the emergence of these large models. So there's probably a whole lot of things we haven't even considered. As we do that, we have a work chapter in your school, foundation models for decision making,. That workshop I hope will be kind of a
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.