cannot train ma-gym environment with IQL about marllib HOT 6 OPEN

Could you please provide me with the complete error tracing log?

from marllib.

sure. I am running the add_new_env.py file. And I have replaced mappo with iql. And the error log is the following,

from marllib.

I met a similar issue. To solve it, import a different ENV_REGISTRY
from marllib.envs.global_reward_env import COOP_ENV_REGISTRY as ENV_REGISTRY
instead of
from marllib.envs.base_env import ENV_REGISTRY

This Is because IQL algorithm is a (fake) VD network that uses run_vd.py to run, when it imports the ENV_REGISTRY, it comes from global_reward_env.

In this add_new_env.py however, the ENV_REGISTRY comes from base_env.

from marllib.

Thank you very much for your reply. But for some reason after replacing that line its telling me that my environment is not registered. Do I have to change something in my config file? Thanks in advance.

from marllib.

Thank you very much for your reply. But for some reason after replacing that line its telling me that my environment is not registered. Do I have to change something in my config file? Thanks in advance.

You can try to register both environment in the registries (base_env and global_reward_env). Also, If you can kindly provide the specific error screenshot you have encountered, I may get a better understanding of what's going on :)

from marllib.

I solved it afterwards. I had to change the init.py file in the marl folder. I had to make the ENV_REGISTRY as COOP_ENV_REGISTRY. After that it worked. Thanks for your help though!

from marllib.