Fido
|
gen | |
GeneticAlgo | Genetic algorithms used to produce fit neural networks |
net | |
Adadelta | An adaptive learning rate Trainer (Zeiler) |
Backpropagation | A classic SGDTrainer |
Layer | A layer in a NeuralNet |
NeuralNet | A neural network |
Neuron | A neuron in a Layer of a NeuralNet |
Pruner | Removes unnecessary neurons from a NeuralNet |
SGDTrainer | A classic backpropagation SGD Trainer |
Trainer | Trains neural networks |
rl | |
FidoControlSystem | A highly effective reinforcement learning control system (Truell and Gruenstein) |
History | |
Wire | A multi-dimensional data point |
Interpolator | An interpolator of multi-dimensional data points |
Learner | A reinforcement learning system |
LSInterpolator | A least squares wire fitted Interpolator |
Model | |
QLearn | A Learner that follows the Q-Learning algorithm |
WireFitQLearn | A Learner using Q-learning that works with continous state action spaces (Gaskett et al.) |
Emitter | |
Line | |
Robby | |
Simlink | A robotic simulator |
TDVect |