We've found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploration method is simple to implement and very rarely decreases performance, so it's worth trying on any problem.
We've created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once.
This post describes four projects that share a common theme of enhancing or using generative models, a branch of unsupervised learning techniques in machine learning.
