Function train_one_step

pytorch/rl_trader.py:123–137

(model, criterion, optimizer, inputs, targets)

def train_one_step(model, criterion, optimizer, inputs, targets):
  # convert to tensors
  inputs = torch.from_numpy(inputs.astype(np.float32))
  targets = torch.from_numpy(targets.astype(np.float32))

  # zero the parameter gradients
  optimizer.zero_grad()

  # Forward pass
  outputs = model(inputs)
  loss = criterion(outputs, targets)
        
  # Backward and optimize
  loss.backward()
  optimizer.step()