How We Used Reinforcement Learning to Solve the Abbey of Crime

Explore the fascinating journey of using Reinforcement Learning to conquer the Abbey of Crime, a groundbreaking 8-bit RPG from 1987, in this captivating conference talk. Delve into the technological marvel of this 2.5D game, which managed to pack sound, images, program logic, and data into a mere 120k. Discover how an AI was designed and built to autonomously play and complete one of the most challenging games ever developed. Gain insights into the innovative application of machine learning techniques to solve complex gaming scenarios and understand the intricacies of this pioneering project.