I am currently working on artificial curiosity for robots. The goal here is to let the robot explore its environment independently to improve its model of the world. It receives positive feedback whenever the model improves, thus leading it to situations where it can still learn something new about the world. Already familiar places quickly become boring and will be left for more interesting new teritory. You can learn more about this on Jürgen Schmidhuber's website about artificial curiosity.
PyBrainThe acronym PyBrain stands for "Python-based Reinforcement Learning, Artificial Intelligence and Neural Networks" and is the name of our machine learning library, that we currently develop. We are still in an early development stage but more information and the source code (the library is freeware) will be available on the PyBrain website.
Policy Gradients for RobotsIn order to use reinforcement learning on real robots, a method for dealing with continuous states and actions is needed. Policy Gradients is one such method, and it works quite well in our simulations (check out the videos). However, the current exploration strategy is somewhat inefficient, as it adds some randomness to the action in each single time-step. I am currently developing a more global exploration strategy that uses random strategies rather than single actions. In the videos below, you can see both methods compared to each other. Or download the 12 minute uncut learning video (Quicktime Movie format, 30MB).