Is this project implemented in carla?

Is there any code to run the simulator with pre-trained checkpoint?

Do you have a trained DDPG model to share with you, thank you very much

I have been training it for about 4000 episodes(about 7 hours on one NVIDIA GeForce GTX1060 GPU), but the performance is still not good.I don't know how to observe the training process such as loss with the help of tensorboard. Could you please give me some advice?

merged = tf.summary.merge_all()
sess.run(merged,feed_dict={})

1.Where should I run merged?
2.What is the content of the feed_dict?

I believe your paper and code are both excellent.What I am worried about is whether rl algorithms can work as well as the paper.

Hi, thanks for sharing and all the efforts. To make sure is the available checkpoint ("image_agent/ckpt"), the retrained model for CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving paper or it is same with CoRL-2017 model?

Hi! I wonder whether my running is true or not.
When I tried to run Main.py, I found that it finished quickly, that seems it didn't train. And when I made a debug, I found env.reset() always didn't work. And I got an error like this:
self.planner = Planner(self.scene.map_name)
AttributeError:map_name

This error didn't occur if I run carla_env.py directly.
Could you help me? Thank you so much!!!