GitHub - MickyDowns/deep-theano-rnn-lstm-car: Pack of Drones: Layered reinforcement learning (Q-learning w/ RNN) for complex "hunt" behaviorsDrone movement and coordination are learned thru five independently-trained neural networks in four categories of operation. Specifically: avoid: The first two neural networks enable the drone to avoid obstacles. The turn RNN trains a drone moving at constant speed to avoid stationary and moving obstacles. Inputs are a set of five sonar sensor readings that emanate from the front of the drone. Out
