Max Schwarzer
TalkRL: The Reinforcement Learning Podcast
The Advantages of Model-Based and Model-Free Algorithms
As you're going toward the asymptote, I would expect Model 3 to generally have an advantage in computational efficiency. That said, I do sort of think that model-based and model-free algorithms are actually moving towards a position where they're surprisingly equivalent. As we work out the kinks in each class of algorithm, you get closer and closer to optimal performance.
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.
