Deciphering Reward Functions
Minqi and Marc delve into the complexities of defining reward functions in machine learning, emphasizing the challenge of determining what constitutes a sufficient reward. They explore the concept of auto curricula and environment design as key factors in training more general agents. The discussion also touches on the importance of models generating their own theories to enhance their understanding of the world.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Can we build a generalist agent? Dr. Minqi Jiang and Dr. Marc Rigter
Related Questions