public void Learn()
{
List <FloatTensor> rewards_list = new List <FloatTensor>();
List <FloatTensor> losses_list = new List <FloatTensor>();
for (int i = 0; i < history.Count; i++)
{
if (history[i][1] != null)
{
rewards_list.Add(history[i][1]);
}
if (history[i][0] != null)
{
losses_list.Add(history[i][0]);
}
}
FloatTensor rewards = Functional.Concatenate(this.controller.floatTensorFactory, rewards_list, 0);
FloatTensor losses = Functional.Concatenate(this.controller.floatTensorFactory, losses_list, 0);
var norm_rewards = rewards.Sub(rewards.Mean()).Div(rewards.Std().Add(0.000001f));
norm_rewards.Autograd = true;
var policy_loss = norm_rewards.Mul(losses.Neg()).Sum(0);
policy_loss.Backward();
optimizer.Step(rewards.Shape[0], 0);
history = new List <FloatTensor[]>();
}