sufengniu / gym_torcs_rl Goto Github PK

I see this project in this repositories.'gym_torcs_rl/testing/DDPG-Keras-Torcs/'.In this project ,I see you use image as the input for the network.I want to know.Do you use the pretrained 'guide network' to train actor or critic?On the other hand,you only use image as the input,but not conclude the 'guide network'.Because I also need to slove this has 'guide net' DDPG,but I have many difficult.So I want to need your help.Can you help me?Thanks!
(Note: Well,I mean is this should have three network)
Thanks!

Hi, so nice to find your project. Any progress on changing the rewards? It takes such a long time to train....

Hi,I see the code in your repositories.'gym_torcs_rl/testing/DDPG-Keras-Torcs/''.I find this project use image as the input.But when I run the code ,I have some errors,and the car don't move .like this:
'Episode : 0 Replay Buffer 0
Client connected on 3101..............
AL lib: (WW) alSetError: Error generated on context 0x56256fbb9b00, code 0xa005
OpenAL backend info:
Vendor: OpenAL Community
Renderer: OpenAL Soft
Version: 1.1 ALSOFT 1.18.2
Available sources: 256
Available buffers: 1024 or more
Dynamic Sources: requested: 235, created: 235
#static sources: 21
#dyn sources : 235
sw 64 - sh 64 - vw 64 - vh 64 - imgsize 12288
Traceback (most recent call last):
File "ddpg.py", line 185, in
playGame()
File "ddpg.py", line 105, in playGame
a_t_original = actor.model.predict(s_t.reshape(1, s_t.shape[0]), s_ti)
File "/home/bcwang/Applications/anaconda3/envs/ddpg_env/lib/python3.5/site-packages/keras/engine/training.py", line 1161, in predict
check_batch_dim=False)
File "/home/bcwang/Applications/anaconda3/envs/ddpg_env/lib/python3.5/site-packages/keras/engine/training.py", line 76, in standardize_input_data
'Found: array with shape ' + str(data.shape))
Exception: The model expects 2 input arrays, but only received one array. Found: array with shape (1, 29)
Timeout for client answer
Timeout for client answer
Timeout for client answer
Timeout for client answer
Timeout for client answer
Timeout for client answer
Timeout for client answer
Timeout for client answer
Timeout for client answer
Timeout for client answer
Timeout for client answer
Timeout for client answer
Timeout for client answer'
Do you know how to solve this problem?Can you help me?Thanks!