The Teachingbox uses advanced machine learning techniques to relieve developers from the programming of hand-crafted sophisticated behaviors of autonomous agents (such as robots, game players etc...) In the current status we have implemented a well founded reinforcement learning core in Java with many popular usecases, environments, policies and learners.
Important note: We are currently not offering any release packages! Instead, please checkout the SVN trunk for obtainig the latest version of the Teachingbox:
svn checkout https://svn.code.sf.net/p/teachingbox/code/trunk teachingbox-trunk
or browse files: https://sourceforge.net/p/teachingbox/code/HEAD/tree/trunk/
- Reinforcement Learning
- RL-Environments: nArmedBandit, WindyGridWorld, MountainCar, PoleBalance, PoleSwingUp, CartPole, RL-Glue, DynamicalSystems, Grid-Worlds such as Cliff-Walking (including an Grid-World Editor), Crawling Robot 3D Simulation (PythonGL), etc.
- RL-Learner: RBF, Tabular, TileCoding, Neural-Fitted Q-Iteration
- RL-Policies: Greedy, EpsilonGreedy, Softmax, VDBE / VDBE-Softmax, REINFORCE
- Visualizations: Mountain-Car, PoleBalance, Crawler 3D
Be the first to post a review of Teachingbox!