This repository hosts a customized PPO based agent for Carla. The goal of this project is to make it easier to interact with and experiment in Carla with reinforcement learning based agents -- this, by wrapping Carla in a gym like environment that can handle custom reward functions, custom debug output, etc.
When I run python3 Carla-ppo/train.py --model_name model1 -start_carla I get the following output:
free(): invalid pointer
As recommended, I'm using Carla 0.9.5.
The manual control script (PythonAPI/examples/manual_control.py) that comes with Carla works without any issues.
Any ideas what the issue could be?
When I run
python3 Carla-ppo/train.py --model_name model1 -start_carlaI get the following output:As recommended, I'm using Carla 0.9.5. The manual control script (
PythonAPI/examples/manual_control.py) that comes with Carla works without any issues. Any ideas what the issue could be?