Evolutionary Algorithms vs. Gradient Methods
Julian discusses the integration of gradient methods with quality diversity algorithms, highlighting the importance of undirected mutation in future learning algorithms. Tim emphasizes the significance of keeping options open, influenced by Kenneth's insights on deception in search spaces.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#81 JULIAN TOGELIUS, Prof. KEN STANLEY - AGI, Games, Diversity & Creativity [UNPLUGGED]
Related Questions