Learning from Mistakes
Julia explains how deep reinforcement learning works by rewarding good decisions and penalizing less productive ones. Jim shares his experience of never overriding models, including during the great financial crisis and the dot bomb. They discuss how deep reinforcement learning helps in quickly adapting to changes in regimes and timing factors.In this clip
From this podcast

Infinite Loops 2022
Ep.135 — A Deep Dive into Deep Reinforcement Learning w/ Julia Bonafede
Related Questions