Machine Learning, Robotics, Reinforcement Learning
TU Darmstadt, FG-IAS
Hochschulstr. 10, 64289 Darmstadt
Office. Room E225, Building S2|02
His master's thesis entitled "Nonparametric Off-Policy Policy Gradient" was written at IAS, supervised by Samuele Tosatto, and explored an approach to obtain an off-policy gradient update with better sample-efficiency.