Closed WangJuan6 closed 3 months ago
Hi, I read the code and I think the reason is that the value of the encoderhiddensize_list
is not adapted to the values of critic_headhiddensize and actor_headhiddensize:
I am not sure my understanding is correct, but I hope it can be of help.
You should keep the last element in encoder_hidden_size_list
as the same as the number of critic_head_hidden_size
. In the default arguments of VAC, they are both 64.
BTW, you can directly print this nn.Module to examine the concrete network layer settings.
I modified the parameters:
into:
critic_head_hidden_size
It works, thanks for your reply!
Dear Author, I want to handle the complex observation, and I ran the code by python ding/example/ppo_with_complex_obs.py. However, I got an error:
Can you help me to solve this problem? Thanks