angelomorgado/carla-gymdrive

Autonomous driving episode generation for the Carla simulator in a gym environment. This framework makes it easy to create driving scenarios to train/test the agent.

carla-gymdrive's Issues

Error! When Run train_agent_stablebaselines3.py and train_dqn_agent.py

• carla server : I use 0.9.15 vesrion docker , and start it manually.
• conda env: create with carla_0.9.15_virtual_env.yml and requirements.txt
• ubuntu 20.04, GPU 3090

when I run train_agent_stablebaselines3.py, first raise this error
RuntimeError: mat1 and mat2 shapes cannot be multiplied (2x2 and 768x64)
I find this error is from the wrong output of CustomExtractor_PPO
Then I change the output of the CustomExtractor_PPO(custom_feature_extractor.py), return combined_features instead of policy_output
Then raise this error
ValueError: Expected parameter loc (Tensor of shape (1, 2)) of distribution Normal(loc: torch.Size([1, 2]), scale: torch.Size([1, 2])) to satisfy the constraint Real(), but found invalid values:
tensor([[nan, nan]], device='cuda:0')

I have no idea why i got this error, please help me~

do you need with the code? I can contribute if you want