2026 03 03 wharton oid seminar
Gave two talks at Wharton’s OID seminar, hosted by Hamsa Bastani: one on teaching with AI, and one on Relative Monte Carlo, our new policy gradient method for reinforcement learning.
Gave two talks at Wharton’s OID seminar, hosted by Hamsa Bastani: one on teaching with AI, and one on Relative Monte Carlo, our new policy gradient method for reinforcement learning.