import gymnasium as gym
import math
import random
import matplotlib
import matplotlib.pyplot as plt
from collections import namedtuple, deque
from itertools import count

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F

env = gym.make("CartPole-v1")

# set up matplotlib
is_ipython = 'inline' in matplotlib.get_backend()
if is_ipython:
    from IPython import display

plt.ion()

# if GPU is to be used
[device](https://docs.pytorch.org/docs/stable/tensor_attributes.html#torch.device "torch.device") = [torch.device](https://docs.pytorch.org/docs/stable/tensor_attributes.html#torch.device "torch.device")(
    "cuda" if [torch.cuda.is_available](https://docs.pytorch.org/docs/stable/generated/torch.cuda.is_available.html#torch.cuda.is_available "torch.cuda.is_available")() else
    "mps" if [torch.backends.mps.is_available](https://docs.pytorch.org/docs/stable/backends.html#torch.backends.mps.is_available "torch.backends.mps.is_available")() else
    "cpu"
)


# To ensure reproducibility during training, you can fix the random seeds
# by uncommenting the lines below. This makes the results consistent across
# runs, which is helpful for debugging or comparing different approaches.
#
# That said, allowing randomness can be beneficial in practice, as it lets
# the model explore different training trajectories.


# seed = 42
# random.seed(seed)
# torch.manual_seed(seed)
# env.reset(seed=seed)
# env.action_space.seed(seed)
# env.observation_space.seed(seed)
# if torch.cuda.is_available():
#     torch.cuda.manual_seed(seed)