Swain

we will restart this demo in February 28th, and we expect to finish it in a week.

Can you offer your launch script or main entry file to help us reproduce your result?

Can you provide more details, like screen snapshots of your errors?

This error could be a repeat register error, which is caused by the repeat import of `GymHybridEnv`. For simplicity, you can modify line 14 like `@ENV_REGISTRY.register('gym_hybrid', force_overwrite=True)` to figure it...

> Also please let me know, why am i getting this error when i run the [DI-engine](https://github.com/opendilab/DI-engine)/[dizoo](https://github.com/opendilab/DI-engine/tree/main/dizoo)/[gym_hybrid](https://github.com/opendilab/DI-engine/tree/main/dizoo/gym_hybrid)/[entry](https://github.com/opendilab/DI-engine/tree/main/dizoo/gym_hybrid/entry)/gym_hybrid_ddpg_main.py code??  For this problem, you should add `replay_path` field in your config,...

For more detailed discussion, you can join our slack channel and some message to us.

- envs: the wrapper which transform original gym env into DI-engine's format - config: the configuration file which contains the setting of `Algorithm + Env` (nested dict) and the default...

Conclusion: `SlimeVolley-v0` env is too **tiny** to fully utilize cpu when training. You can try this test file for env, just run `pytest -sv .` and run `htop` in another...

Our efficiency experiments on Atari/Mujoco environments are comparable with stable-basline3/tianshou. And our mock test benchmark results are shown in this [link](https://opendilab.github.io/DI-engine/feature/collector_overview_en.html). For you test results in `cartpole` env, I will...

> Hello, this is a serious system design problem, which may require fundamental refactor of the framework. Need some guys familiar with framework and system design to work on this....