
Aravind Srinivas 2
TalkRL: The Reinforcement Learning Podcast
00:00
The Trend Doesn't Look to Stop the Continued Diversity
The diversity and range of all these complicated mechanisms people have come up with is absolutely incredible and kind of very strange. And I don't think it should stop because I mean people have the freedom to do any kind of research. It's more the norm that people are kind of tired of just seeing countless new variants of Q learning algorithms promising like one or two percent improvement over existing ones.
Transcript
Play full episode