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