Reinforcement Learning Critique
Tim and Julian discuss the tendency of reinforcement learning algorithms to memorize environments due to the ease of learning, contrasting it with the advantages of making larger stochastic changes in evolutionary computation. They delve into the limitations of gradient descent and the need for more complex representations in learning.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#81 JULIAN TOGELIUS, Prof. KEN STANLEY - AGI, Games, Diversity & Creativity [UNPLUGGED]
Related Questions