Episode 22: Archit Sharma, Stanford, on unsupervised and autonomous reinforcement learning
Generally Intelligent
00:00
Introduction
Archet Sharma is a PhD student at Stanford, advised by Chelsea Finn. His recent work is focused on autonomous deep reinforcement learning. He was an AI resident at Google Brain and he interned with Yasho Benjio at Milla. Archet: "I find myself very lucky because there's very few people who get to take the trajectory"
Transcript
Play full episode
