Description
Hello,
Thank you for sharing your excellent work and providing the code!
While following the instructions in the Usage section, I encountered a few issues and would appreciate some clarification:
Missing train_GPOA.py:
The Usage section states to run python train_GPOA.py for PPO training, but there is no train_GPOA.py file in the repository.
Difference between Repository Code and Paper Description:
Instead of train_GPOA.py, there is a train_PPO.py file. However, it appears that this script does not use DQN as described in the paper, but rather implements a simple Q-table approach. (I also noticed that a previous issue briefly mentioned this.)
Could you clarify whether the PPO implementation using DQN (as described in the paper) is available, or if there are any plans to release the train_GPOA.py script? Any guidance on how to reproduce the results reported in the paper would be greatly appreciated.
Thank you!