public void AsyncUpdate(Optimizer p_optimizer)
{
AsyncUpdate(p_optimizer._dW, p_optimizer._db);
}
public ActorCritic(Optimizer p_optimizer, NeuralNetwork p_network, float p_gamma)
{
_optimizer = p_optimizer;
_network = p_network;
_gamma = p_gamma;
}
public AsyncDoubleQLearning(Optimizer p_optimizer, NeuralNetwork p_networkQ, NeuralNetwork p_networkQt, float p_gamma, int p_asynchUpdate) : base(p_optimizer, p_networkQ, p_networkQt, p_gamma, p_asynchUpdate)
{
}
public QLearning(Optimizer p_optimizer, NeuralNetwork p_network, float p_gamma)
{
_optimizer = p_optimizer;
_network = p_network;
_gamma = p_gamma;
}
public DeepDoubleQLearning(Optimizer p_optimizer, NeuralNetwork p_network, float p_gamma, int p_capacity, int p_batchSize, int p_qtUpdateSize) : base(p_optimizer, p_network, p_gamma, p_capacity, p_batchSize, p_qtUpdateSize)
{
}