how can i solve "empty() received an invalid combination of arguments - got (tuple, dtype=NoneType, device=NoneType)" in MushroomRL?

I'm using MushroomRL for a Deep Reinforcement Learning project, and I'm using a Graph representation as RL Environment where the number of nodes represents the number of actions now in my neural network the input is one value ex: tensor([[5.]], and the output Q is the number of nodes which is ten ex: tensor([[5972.4927, 8562.3330, 7443.6479, 7326.1587, 6615.2090, 6617.3145,6911.8672, 8233.7930, 6821.0093, 7000.1182,]] now I'm using a new framework called MushroomRL, and this is the code

if __name__ == '__main__':
from mushroom_rl.core import Core
from mushroom_rl.algorithms.value import TrueOnlineSARSALambda
from mushroom_rl.policy import EpsGreedy
from mushroom_rl.features import Features
from mushroom_rl.features.tiles import Tiles
from mushroom_rl.utils.dataset import compute_J
from mushroom_rl.utils.parameters import LinearParameter, Parameter
from mushroom_rl.approximators.parametric import TorchApproximator
from mushroom_rl.algorithms.value import DQN



# Set the seed
np.random.seed(1)

# Create the toy environment with default parameters
#mdp = Environment.make('graph_env')
mdp=graph_env()
    # Using an epsilon-greedy policy

epsilon = Parameter(value=0.1)
pi = EpsGreedy(epsilon=epsilon)

# Policy
epsilon = LinearParameter(value=1.,
                          threshold_value=.1,
                          n=1000000)
epsilon_test = Parameter(value=.05)
epsilon_random = Parameter(value=1)
pi = EpsGreedy(epsilon=epsilon_random)




approximator_params = dict(
    network=Network,
    input_shape=(1,),
    output_shape=(1,),
    n_actions=mdp.info.action_space.n,
    optimizer=optimizer,
    loss=F.mse_loss
)

approximator = TorchApproximator

algorithm_params = dict(
batch_size=32,
target_update_frequency=target_update_frequency // train_frequency,
replay_memory=True,
initial_replay_size=initial_replay_size,
max_replay_size=max_replay_size
)

agent=agent = DQN(mdp.info, pi, approximator,
        approximator_params=approximator_params,
        **algorithm_params)

# Algorithm
core = Core(agent, mdp)


# RUN

# Fill replay memory with random dataset
print_epoch(0)
core.learn(n_steps=initial_replay_size,n_steps_per_fit=initial_replay_size)

# Evaluate initial policy
pi.set_epsilon(epsilon_test)
#mdp.set_episode_end(False)
dataset = core.evaluate(n_steps=test_samples)
scores.append(get_stats(dataset))

for n_epoch in range(1, max_steps // evaluation_frequency + 1):
    print_epoch(n_epoch)
    print('- Learning:')
    # learning step
    pi.set_epsilon(epsilon)
    mdp.set_episode_end(True)
    core.learn(n_steps=evaluation_frequency,
              n_steps_per_fit=train_frequency)

    print('- Evaluation:')
    # evaluation step
    pi.set_epsilon(epsilon_test)
    mdp.set_episode_end(False)
    dataset = core.evaluate(n_steps=test_samples)
    scores.append(get_stats(dataset))

it givs me this error when i run the code

TypeError: empty() received an invalid combination of arguments - got (tuple, dtype=NoneType, device=NoneType), but expected one of:
 * (tuple of ints size, *, tuple of names names, torch.memory_format memory_format, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
 * (tuple of ints size, *, torch.memory_format memory_format, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)

i beleve the proplem in part of the code can any one help to fix it ?