def make_environment(env_name: str, seed: int = None) -> gym.Env:
"""
Initialise gym environment
Args:
env_name: environment name or tag
seed: value to seed the environment RNG for reproducibility
Returns:
gym environment
"""
env = make_environment(env_name)
if seed:
env.seed(seed)
return env
def setUp(self) -> None:
self.state = torch.rand(32, 4, 84, 84)
self.next_state = torch.rand(32, 4, 84, 84)
self.action = torch.ones([32])
self.reward = torch.ones([32])
self.done = torch.zeros([32]).long()
self.batch = (self.state, self.action, self.reward, self.done, self.next_state)
self.env = make_environment("PongNoFrameskip-v4")
self.obs_shape = self.env.observation_space.shape
self.n_actions = self.env.action_space.n
self.net = CNN(self.obs_shape, self.n_actions)
self.target_net = CNN(self.obs_shape, self.n_actions)