[Python] SUMO RL : 'module’ object is not callable

When I run the following code i get error 'module' object is not callable

if __name__ == "__main__":
env_name = "4x4grid"
register_env(
env_name,
lambda _: ParallelPettingZooEnv(
sumo_rl.parallel_env(
net_file="./4x4-Lucas/4x4.net.xml",
route_file="./4x4-Lucas/4x4c1c2c1c2.rou.xml",
out_csv_name="outputs/4x4grid/ppo",
use_gui=False,
num_seconds=80000,
)
),
)

config = (
PPOConfig()
.environment(env=env_name, disable_env_checking=True)
)

config.env_runners(num_env_runners=4, rollout_fragment_length=128)
config.training(
train_batch_size=512,
use_gae=True,
grad_clip=None,
num_epochs=10)
config.debugging(log_level="ERROR")
config.framework(framework="torch")
config.resources(num_gpus=int(os.environ.get("RLLIB_NUM_GPUS", "0")))

tune.run(
"PPO",
name="PPO",
stop={"timesteps_total": 100000},
checkpoint_freq=10,
storage_path="~/ray_results/" + env_name,
config=config.to_dict(),
)


(SingleAgentEnvRunner pid=11388) Exception raised in creation task: The actor died because of an error raised in its creation task, ray::SingleAgentEnvRunner.__init__() (pid=11388, ip=127.0.0.1, actor_id=a44169f772470169f85ced2001000000, repr=<ray.rllib.env.single_agent_env_runner.SingleAgentEnvRunner object at 0x000002620CC666F0>)
(SingleAgentEnvRunner pid=11388) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(SingleAgentEnvRunner pid=11388) File "C:\Users\thaigiang\AppData\Local\Temp\ipykernel_12400\3020126705.py", line 17, in <lambda>
(SingleAgentEnvRunner pid=11388) File "C:\Users\thaigiang\anaconda3\Lib\site-packages\pettingzoo\utils\conversions.py", line 14, in par_fn
(SingleAgentEnvRunner pid=11388) env = env_fn(**kwargs)
(SingleAgentEnvRunner pid=11388) ^^^^^^^^^^^^^^^^
(SingleAgentEnvRunner pid=11388) File "C:\Users\thaigiang\anaconda3\Lib\site-packages\sumo_rl\environment\env.py", line 32, in env
(SingleAgentEnvRunner pid=11388) env = SumoEnvironmentPZ(**kwargs)
(SingleAgentEnvRunner pid=11388) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(SingleAgentEnvRunner pid=11388) File "C:\Users\thaigiang\anaconda3\Lib\site-packages\sumo_rl\environment\env.py", line 523, in __init__
(SingleAgentEnvRunner pid=11388) self._agent_selector = agent_selector(self.agents)
(SingleAgentEnvRunner pid=11388) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(SingleAgentEnvRunner pid=11388) TypeError: 'module' object is not callable


Environment:
ray[rllib]==2.44.1
python==3.12.7
torch==2.7.0

I have researched and found that the error may arise during the env register process, parallel_env may be a module and not a function. but I don't know how to solve the error.

Continue reading...