Utilizing state-of-art NeuroES and GPGPU to optimize Mario AI

Bachelor thesis English OPEN
Lövgren, Hans;
(2014)
  • Publisher: Blekinge Tekniska Högskola, Institutionen för kreativa teknologier
  • Subject: Reinforcement Learning | Evolution Strategies | GPGPU | Artifical Neural Networks | Computer Sciences | Datavetenskap (datalogi)

Context. Reinforcement Learning (RL) is a time consuming effort that requires a lot of computational power as well. There are mainly two approaches to improving RL efficiency, the theoretical mathematics and algorithmic approach or the practical implementation approach.... View more
Share - Bookmark