Dear Sir/Miss,
I hope this email finds you well.
I am Xia, I have been working with your code, particularly train_all_cl.py and train_all_ippo.py, and encountered an issue while running these scripts. Specifically, I received the following error:
ImportError: cannot import name 'PPOTFPolicy' from 'ray.rllib.agents.ppo.ppo' (/home/xia/anaconda3/envs/copo/lib/python3.7/site-packages/ray/rllib/agents/ppo/ppo.py)
Upon checking the Ray 2.2.0 documentation and files, I noticed that the functions mentioned in the error are indeed missing.
The whole content are shown below,
"from ray.rllib.algorithms.ppo import ( # noqa
ppo_tf_policy,
ppo_torch_policy,
PPO as PPOTrainer,
DEFAULT_CONFIG,
)"
I suspect that there might be a version mismatch or updated dependencies required for the code to run successfully.
Could you please provide any insight or guidance on how to resolve this issue? I am eager to get this working and would greatly appreciate any assistance you can offer.
Thank you for your time and consideration.
Best regards,
Xia