Pengzhi Yang

Firstly I want to say thank you for the amazing project, UUV Simulator! It is really a great implementation for underwater simulation! However, I have a question about its control....

The effect of NormalizedEnv

2

Hi, thank you for this great implementation!! However, I'm not very sure about the effect of normalized_env.py. Actually, if I remove it, the results seem to be worse than not...

Hello everyone. I'm using baseline to train PPO on an RL project with only one agent which is too slow. So are we able to use any API to run...

I'm extremely sorry to ask you so many questions. However, when testing the monodepth network with DPT-large, I found the inference is not fast (in the for loop, each image's...

Hi, I found it hard to make the agent inside VizDoom to move forward for a specific length. There are several limitations on the speed such as the acceleration. How...

Combine with Unity-gym

4

Thank you so much for this great implementation! However, as I'm using it for our deep reinforcement learning training, I'm wondering whether this work could be combined with [Gym](https://github.com/Unity-Technologies/ml-agents/tree/main/gym-unity)? Because...

Hi, I'm trying to use gps information for the robot. But when the robot is 1 meter deeper than the surface, the robot is not able to obtain it any...

Hi everyone, I'm trying to build my own underwater environment. Thus, I'd like to import some of the built objects. However, in cirs.xml, the objects are imported in already. Even...

Hi Linhai, sorry to bother you. I'm trying to train the D3QN in your paper, but actually, the robot can only run in a circle. Did you have a similar...

Hi, thank you for your great work! But is there any smaller dataset that has been split? The one on the project's webpage is too big and I failed to...