-
Notifications
You must be signed in to change notification settings - Fork 371
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Bugs fix and new feature request for gfootball #335
Comments
@ErlebnisW What are these exactly? Should there been bugs in the code, the tests wouldn't have passed. |
/home/usr/anaconda3/envs/di-engine/lib/python3.8/site-packages/dizoo/gfootball/envs/init.py:6: UserWarning: not found gfootball env, please install it So I copied the above folders in to solve this.
ImportError: cannot import name 'BaseEnvInfo' from 'ding.envs' I solved this by delete BaseEnvInfo from import and following lines.
Following bugs can't fix
File "/home/vcis5/anaconda3/envs/di/lib/python3.8/site-packages/ding/envs/env_manager/base_env_manager.py", line 109, in init Can't fix this.
Traceback (most recent call last): Can't fix this.
File "/home/vcis5/anaconda3/envs/di/lib/python3.8/site-packages/ding/torch_utils/checkpoint_helper.py", line 327, in wrapper Can't fix this. |
Hello, thanks for your questions and suggestions. Now in this PR :
We speculate that this may be because pure DQN algorithm lacks the ability to model long sequence dependencies and efficient exploration mechanisms. You can try to adapt advanced algorithms like NGU to the gfootball environment.
Here is the statistics of our training dataset (100 episodes): the mean, max, min of return in the training dataset is -0.12, 4, -3, respectively, which suggests that we should improve the quality of the dataset. Then we test the accuracy in the training dataset (100 episodes) and validation dataset (50 episodes), is 0.9452 and 0.8009. We also found that the accuracy of some action in training dataset is lower than 0.5 which reflects the problem of class imbalance. In order to obtain a good imitation learning performance, we are taking steps to address the above problems, thank you for your patience. Thanks a lot. |
Thanks |
Hello, We have reduced the difficulty of the built-in AI in the environment,change the env_id from Regarding the reinforcement learning demo, we are currently trying the R2D2 algorithm (the development version is dizoo/gfootball/entry/gfootball_r2d2_main.py in PR), and we will let you know as soon as we have the results, thank you for your patience and attention. Thanks a lot. |
Thanks a lot! I'll have a try. |
There are many bugs in current vesion of DI-engine(V0.3.1) gfootball environment. I have tried to fix some of those, but some problems still exists which are beyond my ability. So I guess it needs systemic maintenance and updates. As far as the codes I have tested, only files in dizoo/gfootball/envs/tests works well(after some bug fix). And the fundamental features metioned in the doc(play with built-in AI & self-play) are basicly unusable.
Besides, since gfootball is an environment with great potential both in academy and practice. I strongly recommend following features being added:
Thanks. I think DI-engine is an excelent potential framwork, hope it to be better.
The text was updated successfully, but these errors were encountered: