SHITIANYU

Update wave_attenuation.py

3

The previous code can only display one rl vehicle, this way it can display all rl vehicles and their leader and follower vehicles, which is in accordance to the paper....

## Bug Description ValueError: Episode truncation is not supported without a value function. Consider setting batch_mode=complete_episodes. ## Bug Reproduce File in which the bug occurred: `file.py` The exact command that...

cannot run preprocess data(OSError: [Errno 24] Too many open files)

5

When I run python preprocess_data.py -m lanegcn: it will have this error:

How to run in carla 0.9.4

5

It seems that this CARLA version cannot be installed now. Traceback (most recent call last): File "run_CIL.py", line 4, in from carla.driving_benchmark import run_driving_benchmark ModuleNotFoundError: No module named 'carla'

The learning rate for actor and critic is too small, it takes a very long time to converge. Maybe change it as 0.01

How to add new maps for RL agent to learn?

9

Currently, there are only three maps in which RL agent will learn driving. If I want to add more scenarios ( e.g. a straight road with a static obstacle in...

Confusion about the simulation environment

3

Hello, I have a little confusion about the gym-duckietown simulator. My confusion is how does the robot moves forward and avoids obstacles? For example, in the [PID controller](https://github.com/rizavelioglu/challenge-aido_RL-IL/blob/master/tutorials/PIDcontroller.py) script, I...

torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

1

may i know if this issue is my memory is not enough? ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 1622990) of binary: /home/changquan/anaconda3/envs/lang/bin/python Traceback (most recent call last): File "/home/changquan/anaconda3/envs/lang/bin/torchrun", line...

如何增加prompt呢？

2

### Is your feature request related to a problem? Please describe. 我目前想控制通过做ptuning去控制模型说话风格，比如按照杠精的说话风格 ### Solutions 我想自己定义一个prompt加入到puning 过程中（https://github.com/THUDM/ChatGLM-6B/blob/main/ptuning/train.sh） 比如，“假设你是一个杠精正在和用户聊天，请根据{input}回复：“ 请问应该如何添加呢？ ### Additional context _No response_

how to download the dataset?

1

when i click on this link: https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset It says no able to see the data: