Integrating deep reinforcement learning agents with the C. elegans nervous system. Chenguang Li, Gabriel Kreiman, Sharad Ramanathan
The 2021 Thomas Temple Hoopes Prize is awarded
for excellent undergraduate work
Stephen Casper is a 2021 awardee for his submission entitled “Efficient and Insidious Adversaries in Deep Reinforcement Learning”—supervised and nominated by Professor Gabriel Kreiman
Efficient and insidious adversaries in deep reinforcement learning. Stephen Casper. Harvard University (2021).
Read his thesis here.