avisingh599 / imitation-dagger Goto Github PK

I am trying to refactor the code to work with 1/10 car http://donkeycar.com.
But i wanted to know few things in gym_torcs.py line 72
action_torcs = client.R.d and line 127 obs = client.S.d is n't those actions are the same or i am missing something?

Hi, first of all, many thanks for your great work.

I got a problem and don't know whether it is caused by torcs' update or my misunderstanding.

• If I simply run python dagger.py, I will get Timeout for client answer.
• If I set up the server on another terminal and initialize the game as shown in gym_torcs, then when I run python dagger.py, I will got this:

cannot bind socketClient connected on 3101..............
Traceback (most recent call last):
  File "dagger.py", line 30, in <module>
    ob = env.reset(relaunch=True)
  File "/home/hao/Workspace/imitation-dagger/gym_torcs.py", line 190, in reset
    self.observation = self.make_observaton(obs)
  File "/home/hao/Workspace/imitation-dagger/gym_torcs.py", line 270, in make_observaton
    image_rgb = self.obs_vision_to_image_rgb(raw_obs[names[8]])
KeyError: 'img'

Thanks in advance.

Hello Avi,

I'm trying to implement your dagger.py code as is. When I run the code, I noticed that the loss saturates to 0.9453 in the first run itself (within the first few epochs), even before dagger iters start (in iter1 of dagger it satures to 1.0715). Can you mention what kind of losses you get at each run of your network? This would help in debugging.

It is kind of frustrating that I'm unable to replicate your performance. I'm new to tensorflow-keras-python environments, but I'm very interested and your repo seemed like a good place to start tinkering. Do you suspect some network and torcs setup issues? Can you mention what versions of keras, torcs, etc you have used and on what hardware? I'd be grateful for any help in getting me out of this local minima :/

Quick Update: I changed the output activation to 'linear' and Adam's lr to 1e-3. This worked like a charm. It crashes at 134th step in iter1, 539th step in iter2, and the goes the distance. This was relieving :D However, it's still weird that I can't get the 'tanh' activation to work.

Hi, after I cloned your repo and ran the dagger.py, the model doesn't seem to improve. In fact, it stops at 28 iterations every time. I didn't change any parameter in your code. So could you please take a look at it? Also, how did you get those .gif on the README? Are those just from the TORCS visualization?