Haofei Lu

> As I told you by e-mail, I appreciate your findings! I'll fix them and update the arxiv submission and I will ask the chair of CVPR 2022 whether I...

> If I am not mistaken, the two versions you mentioned only differ by the output of the Affine layer. The first version only multiplies. The second version also adds....

> There are 3 questions: > > 1. Does the size of zsem has anything to do with the shape of the image? > Answer: No, they are independent. zsem...

> There are 3 questions: > > 1. Does the size of zsem has anything to do with the shape of the image? > Answer: No, they are independent. zsem...

> Hi @Josh00-Lu thanks for the PR. Have you had cases where handling termination / truncation has made a huge difference in the performance? Yes. Especially for mujoco environments like...

> +1 on massive improvements using the PR's changes. I have a custom quadrotor improvement, that works well with SB3, but implementation of cleanRL gave poor performances, including catastrophic forgetting...

> Sorry for the late message, personally, I would advocate for a separate file with this implementation if the original isn't wanting to be changed. This would prevent the problem...

> > Another one is https://github.com/openai/guided-diffusion/blob/main/guided_diffusion/gaussian_diffusion.py#L709 > > It starts from guided_diffusion/scripts/image_nll.py > > This is easy to follow and the result makes sense (close to the table reported) Thanks...

What if there is a "maths explanation" will be better! Whatever, thanks a lot!

I have solved the problem. But I encountered another :( Now, I only use ```shell python -m lamorel_launcher.launch --config-path Absolute/Path/To/Grounding_LLMs_with_online_RL/experiments/configs --config-name local_gpu_config rl_script_args.path=Absolute/Path/To/Grounding_LLMs_with_online_RL/experiments/train_language_agent.py lamorel_args.accelerate_args.machine_rank=0 ``` As you mentioned in https://github.com/flowersteam/lamorel/issues/23#issuecomment-1790381781...