Undergraduate Research & Scholarships

Alvin Wan Rose Hills

Evolution Strategies as Derivative Free Alternative to Deep Reinforcement Learning

Deep Reinforcement Learning (DRL) has seen state-of-the-art results with Atari games, spoken dialogue systems, and a differentiable neural computer. However, excessive amounts of computer power are required to attain such results. My work concerns potential simplifications of DRL so that more advanced tasks are feasible, leveraging alternative evolutionary strategies with deep function approximators and evolutionary strategies with linear function approximators.

Message To Sponsor

Thank you very much for this opportunity! It's given me the opportunity to interact with many other fields and pursue something I truly believe will advance the state of self-driving cars. My hope is that I can find donors as generous as yourself in the future. My future plan is still to apply to graduate school.