how can I use metadrive environment? about marllib HOT 3 CLOSED

(marllib) oscar@dl:~/msc/MARLlib$ python marl/main.py --algo_config=mappo --env_config=metadrive with env_args.map_name=Roundabout
/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/scipy/__init__.py:143: UserWarning: A NumPy version >=1.19.5 and <1.27.0 is required for this version of SciPy (detected version 1.19.3)
  warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
It seems you don't install our cython utilities yet! Please reinstall MetaDrive via: <pip install -e .> or <pip install metadrive>! But don't worry! We are now falling back to native python implementation!
WARNING:root:It seems you don't install our cython utilities yet! Please reinstall MetaDrive via: <pip install -e .> or <pip install metadrive>! But don't worry! We are now falling back to native python implementation!
It seems you don't install our cython utilities yet! Please reinstall MetaDrive via: <pip install -e .> or <pip install metadrive>! But don't worry! We are now falling back to native python implementation!
WARNING:root:It seems you don't install our cython utilities yet! Please reinstall MetaDrive via: <pip install -e .> or <pip install metadrive>! But don't worry! We are now falling back to native python implementation!
Successfully registered the following environments: ['MetaDrive-test-v0', 'MetaDrive-validation-v0', 'MetaDrive-v0', 'MetaDrive-10envs-v0', 'MetaDrive-1000envs-v0', 'MetaDrive-training0-v0', 'MetaDrive-training1-v0', 'MetaDrive-training2-v0'].
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
| Env_Name   | Check_Status   | Error_Log                           | Config_File_Location                | Env_File_Location          |
+============+================+=====================================+=====================================+============================+
| mpe        | Error          | No module named 'numpy.typing'      | envs/base_env/config/mpe.yaml       | envs/base_env/mpe.py       |
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
| mamujoco   | Error          | No module named 'multiagent_mujoco' | envs/base_env/config/mamujoco.yaml  | envs/base_env/mamujoco.py  |
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
| smac       | Error          | No module named 'smac'              | envs/base_env/config/smac.yaml      | envs/base_env/smac.py      |
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
| football   | Error          | No module named 'gfootball'         | envs/base_env/config/football.yaml  | envs/base_env/football.py  |
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
| magent     | Error          | No module named 'numpy.typing'      | envs/base_env/config/magent.yaml    | envs/base_env/magent.py    |
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
| rware      | Error          | No module named 'rware'             | envs/base_env/config/rware.yaml     | envs/base_env/rware.py     |
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
| lbf        | Error          | No module named 'lbforaging'        | envs/base_env/config/lbf.yaml       | envs/base_env/lbf.py       |
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
| pommerman  | Error          | No module named 'pommerman'         | envs/base_env/config/pommerman.yaml | envs/base_env/pommerman.py |
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
| hanabi     | Error          | No module named 'cffi'              | envs/base_env/config/hanabi.yaml    | envs/base_env/hanabi.py    |
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
| metadrive  | Ready          | Null                                | envs/base_env/config/metadrive.yaml | envs/base_env/metadrive.py |
+------------+----------------+-------------------------------------+-------------------------------------+----------------------------+
use fc encoder
(pid=12551) /home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/scipy/__init__.py:143: UserWarning: A NumPy version >=1.19.5 and <1.27.0 is required for this version of SciPy (detected version 1.19.3)
(pid=12551)   warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
== Status ==
Current time: 2023-02-01 07:55:05 (running for 00:00:01.17)
Memory usage on this node: 2.6/31.3 GiB
Using FIFO scheduling algorithm.
Resources requested: 1.0/8 CPUs, 1.0/2 GPUs, 0.0/17.85 GiB heap, 0.0/8.92 GiB objects (0.0/1.0 accelerator_type:G)
Result logdir: /home/oscar/ray_results/mappo_gru_Roundabout
Number of trials: 1/1 (1 RUNNING)
+-----------------------------------------------+----------+-------+
| Trial name                                    | status   | loc   |
|-----------------------------------------------+----------+-------|
| MAPPOTrainer_metadrive_Roundabout_bcdde_00000 | RUNNING  |       |
+-----------------------------------------------+----------+-------+


2023-02-01 07:55:05,771 ERROR trial_runner.py:924 -- Trial MAPPOTrainer_metadrive_Roundabout_bcdde_00000: Error processing event.
Traceback (most recent call last):
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/tune/trial_runner.py", line 890, in _process_trial
    results = self.trial_executor.fetch_result(trial)
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/tune/ray_trial_executor.py", line 788, in fetch_result
    result = ray.get(trial_future[0], timeout=DEFAULT_GET_TIMEOUT)
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/_private/client_mode_hook.py", line 105, in wrapper
    return func(*args, **kwargs)
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/worker.py", line 1627, in get
    raise value
ray.exceptions.RayActorError: The actor died because of an error raised in its creation task, ray::MAPPOTrainer.__init__() (pid=12551, ip=192.168.0.98)
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/rllib/agents/trainer_template.py", line 137, in __init__
    Trainer.__init__(self, config, env, logger_creator)
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/rllib/agents/trainer.py", line 623, in __init__
    super().__init__(config, logger_creator)
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/tune/trainable.py", line 107, in __init__
    self.setup(copy.deepcopy(self.config))
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/rllib/agents/trainer_template.py", line 147, in setup
    super().setup(config)
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/rllib/agents/trainer.py", line 716, in setup
    self.env_creator = _global_registry.get(ENV_CREATOR, env)
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/tune/registry.py", line 168, in get
    return pickle.loads(value)
  File "/home/oscar/msc/MARLlib/envs/base_env/metadrive.py", line 3, in <module>
    from metadrive.envs.marl_envs import MultiAgentBottleneckEnv, MultiAgentParkingLotEnv, MultiAgentRoundaboutEnv, \
ModuleNotFoundError: No module named 'metadrive.envs'
== Status ==
Current time: 2023-02-01 07:55:05 (running for 00:00:01.17)
Memory usage on this node: 2.6/31.3 GiB
Using FIFO scheduling algorithm.
Resources requested: 0/8 CPUs, 0/2 GPUs, 0.0/17.85 GiB heap, 0.0/8.92 GiB objects (0.0/1.0 accelerator_type:G)
Result logdir: /home/oscar/ray_results/mappo_gru_Roundabout
Number of trials: 1/1 (1 ERROR)
+-----------------------------------------------+----------+-------+
| Trial name                                    | status   | loc   |
|-----------------------------------------------+----------+-------|
| MAPPOTrainer_metadrive_Roundabout_bcdde_00000 | ERROR    |       |
+-----------------------------------------------+----------+-------+
Number of errored trials: 1
+-----------------------------------------------+--------------+----------------------------------------------------------------------------------------------------------------------------+
| Trial name                                    |   # failures | error file                                                                                                                 |
|-----------------------------------------------+--------------+----------------------------------------------------------------------------------------------------------------------------|
| MAPPOTrainer_metadrive_Roundabout_bcdde_00000 |            1 | /home/oscar/ray_results/mappo_gru_Roundabout/MAPPOTrainer_metadrive_Roundabout_bcdde_00000_0_2023-02-01_07-55-04/error.txt |
+-----------------------------------------------+--------------+----------------------------------------------------------------------------------------------------------------------------+

(pid=12551) 2023-02-01 07:55:05,767     ERROR worker.py:425 -- Exception raised in creation task: The actor died because of an error raised in its creation task, ray::MAPPOTrainer.__init__() (pid=12551, ip=192.168.0.98)
(pid=12551)   File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/rllib/agents/trainer_template.py", line 137, in __init__
(pid=12551)     Trainer.__init__(self, config, env, logger_creator)
(pid=12551)   File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/rllib/agents/trainer.py", line 623, in __init__
(pid=12551)     super().__init__(config, logger_creator)
(pid=12551)   File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/tune/trainable.py", line 107, in __init__
(pid=12551)     self.setup(copy.deepcopy(self.config))
(pid=12551)   File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/rllib/agents/trainer_template.py", line 147, in setup
(pid=12551)     super().setup(config)
(pid=12551)   File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/rllib/agents/trainer.py", line 716, in setup
(pid=12551)     self.env_creator = _global_registry.get(ENV_CREATOR, env)
(pid=12551)   File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/tune/registry.py", line 168, in get
(pid=12551)     return pickle.loads(value)
(pid=12551)   File "/home/oscar/msc/MARLlib/envs/base_env/metadrive.py", line 3, in <module>
(pid=12551)     from metadrive.envs.marl_envs import MultiAgentBottleneckEnv, MultiAgentParkingLotEnv, MultiAgentRoundaboutEnv, \
(pid=12551) ModuleNotFoundError: No module named 'metadrive.envs'
Traceback (most recent call last):
  File "marl/main.py", line 55, in <module>
    run_cc(config_dict)
  File "/home/oscar/msc/MARLlib/marl/algos/run_cc.py", line 182, in run_cc
    results = POlICY_REGISTRY[config_dict["algorithm"]](config_dict, common_config, env_info_dict, stop)
  File "/home/oscar/msc/MARLlib/marl/algos/scripts/mappo.py", line 64, in run_mappo
    results = tune.run(MAPPOTrainer,
  File "/home/oscar/anaconda3/envs/marllib/lib/python3.8/site-packages/ray/tune/tune.py", line 624, in run
    raise TuneError("Trials did not complete", incomplete_trials)
ray.tune.error.TuneError: ('Trials did not complete', [MAPPOTrainer_metadrive_Roundabout_bcdde_00000])