A thoughtful engagement with Sutton's RL-centric view of AI, arguing imitation learning and RL are complementary rather than opposed and unpacking the continual-learning bottleneck — useful framing for anyone reasoning about where agent learning is headed.
I have a much better understanding of Sutton’s perspective now.
I wanted to reflect on it a bit.
(00:00:00) - The steelman (00:02:42) - TLDR of my current thoughts (00:03:22) - Imitation learning is continuous with and complementary to RL (00:08:26) - Continual learning (00:10:31) - Concluding thoughts Get full access to Dwarkesh Podcast at www.dwarkesh.com/subscribe
Transcript
I have a much better understanding of Sutton’s perspective now. I wanted to reflect on it a bit. (00:00:00) - The steelman (00:02:42) - TLDR of my current thoughts (00:03:22) - Imitation learning is continuous with and complementary to RL (00:08:26) - Continual learning (00:10:31) - Concluding thoughts Get full access to Dwarkesh Podcast at www.dwarkesh.com/subscribe
