Thorsten Kurth
Thorsten Kurth
Concerning PPO, the line you are pointing at is just a bias parameter for the previous layer. I think there is a typo there instead of ```actor_biases.push_back(register_parameter("actor_b_entry", torch::zeros(encoder_layer_sizes[0])));``` can you...
As you can see from below, the second parameter in linear is the number of output features and the bias has to have the same shape: ```for (int i =...
Hello Sachin, good to know that it fixed your issue. Looking at the code, I am wondering about multiple things: your nenvs is equal to the rollout buffer size, which...
Also, what are the other settings, are you using squashing or rescaling? And can you please tell me where it fails, I need to see the full error message.
/build_and_test
How does it behave if you pass a kwarg which has already been passed explicitly, for example rank or world_size? Will that overwrite the previous one?
Hello Nathan. In the --no-build-isolation is always required. You say it does not compile with python 3.12 and no build isolation enabled?
Hello Sachin, thanks for reaching out. Can you explain more about your problem? Are the state vectors all of equal shape or do they have different shapes? Concerning the number...
Hello Sachin, this sounds like you can concatenate the three vectors together to form one vector, and on the model size take them apart. Basically create a new vector with...
Hello Sachin, as far as I understand, the paper uses 3 input features, one from each flattened state vector, right? Then they apply an MLP for each of the n_nodes...