Towards More Practical Reinforcement Learning

For example, one game we have experimented on is a puzzle game called Refraction, Reinforcement Learning is beginning to be applied which teaches kids how to multiply fractions by splitting laser outside traditional domains such as robotics, and beams. In this case, we need to choose right sequence of puzzles into human-centric domains such as healthcare and to give to students such that they complete the most concepts education. In these domains, two problems are critical successfully. Making this decision is difficult because to address: We must be able to evaluate algorithms of the large amount of information we can collect about each with a collection of prior data if one is available, student, most of which is not very useful for the task at hand. and we must devise algorithms that carefully Refraction and our other educational games, such as Treefrog trade off exploration and exploitation in such a way Treasure, have each been played by hundreds of thousands that they are guaranteed to converge to optimal behavior of players, providing ample opportunity for learning how to quickly, while retaining very good performance improve these games using data.