Reinforcement Learning in Unity - Teach Your Monsters
With the advent of deep learning many of the tasks in computer science that have been deemed impossible suddenly became only a few clicks away. One of the approaches made available is reinforcement learning - a method for solving problems by establishing an action-reward scheme. Combined with the power and availability of the general-purpose game engines, anyone with a rudimentary knowledge of the topic can create and train their virtual creatures. In this talk we will use this power to solve one of the most frustratingly difficult (according to the internet) games of our era.
Adam is postdoctoral researcher at the German Center for Neurodegenerative Diseases where he applies next-gen technologies to psychology and neuroscience research. Currently he focuses on simulation of human interaction in virtual environments and building of believable digital AI agents with the applications in the treatment of anxiety disorders.