DDPG

DDPG copied to clipboard

File "gym_ddpg.py", line 28 total_reward = 0

kaddinfoo

when I call upon the load_network and save_network, the error pops up. AttributeError: 'ActorNetwork' object has no attribute 'save_network' I am trying to fix this error but until now it...

mudassirej

abhinavsagar

kant

Normalize actor gradients?

1

This gradient for actor needs to be normalized over batch_size? https://github.com/floodsung/DDPG/blob/18825eed85f877b23cf9b531a8c5821d9f956eb2/actor_network_bn.py#L37

panjiangwei

Hello, I meet some problem, when my action dimension equal to one, the result is good, but when my action dimension is two (the activation function is tanh and sigmoid),...

m5823779

AttributeError: 'FilteredEnv' object has no attribute 'monitor'

2

``` Traceback (most recent call last): File "gym_ddpg.py", line 43, in main() File "gym_ddpg.py", line 13, in main env.monitor.start('experiments/' + ENV_NAME,force=True) AttributeError: 'FilteredEnv' object has no attribute 'monitor' ``` ```...

inksci

mjmodel.h: no such file or directory

xiuhui666

Actions generated by Actor network increases to 1. and stay there

1

Hi, Thanks for your code. I tried to use it for training TORCS, however, my result are not good and to be specific after a few steps, actions generated by...

Amir-Ramezani

Thanks for your work! Is your input a image or just a vector? and what is the dimension of your output action?

OsgoodWu