Problem loading csv file for each env while using tune

I am tryin to use tune with ppo. My env loads a csv file but when I am using tune it gives the following error. I think the problem is in loading a csv file to each environment. Can some please tell me how can I resolve this problem.
ERROR worker.py:409 – Exception raised in creation task: The actor died because of an error raised in its creation task, ray::PPO.init() (pid=9584, ip=192.168.0.28)
FileNotFoundError: [Errno 2] No such file or directory:
(pid=15400) Windows fatal exception: access violation
(pid=15400)
(pid=13004) Windows fatal exception: access violation
(pid=13004)
(pid=13900) Windows fatal exception: access violation
FileNotFoundError: [Errno 2] No such file or directory:

If you can upload your code, that’d be helpful in spotting any possible issue. Can you explain how the env loads a csv file?

However, based on your error log shown here, I think it’s just a relative path error. This stackoverflow post explains it: python - FileNotFoundError: [Errno 2] No such file or directory - Stack Overflow.
You can try giving the absolute path to your csv file as part of env_config dictionary into the config parameter for tune.run as shown below:

import gym, ray
from ray.tune.registry import register_env


# I imagine you made your custom environment with gym.Env API.
# Even that is not the case, this overall idea should work.
class YourCustomSimulator(gym.Env):    
    def __init__(self, env_config):
    	path_to_csv = env_config['abs_path_csv']
    	csv_file = open(path_to_csv)
        # Use your csv file.

    	# Other usual Gym-related settings 
        self.action_space = <gym.Space>
        self.observation_space = <gym.Space>
    def reset(self):
        return <obs>
    def step(self, action):
        return <obs>, <reward: float>, <done: bool>, <info: dict>

def env_creator(env_config):
    return YourCustomSimulator(...)  # return an env instance

register_env("your_custom_simulator", env_creator)

config = {
        "env": "your_custom_simulator",
        "env_config": {
            'abs_path_csv': "PATH/TO/CSV.csv"
        },
        # Other training related hyper-parameters
}

tune.run(
    "PPO",
    config=config,
    # Other Tune related settings
)

I hope this helps. If not, please let me know.