DVSA-RL
Reinforcement Learning research on Dynamic Vast Sparse Action space with a turn-based strategy simulator written in Rust, designed to interface with deep reinforcement learning agents.
SHO WATANABE
Nice to meet you. I’m Sho Watanabe, a Master’s student at the University of Tokyo, specializing in control systems and simulation in the Department of Information Physics and Computing. I have been interested in Machine Learning, Deep Learning, Reinforcement Learaning and their applications such as control of cars, robots and drawns.
