-
Hi, very nice code.
I downloaded your code and wanted to create envrinoment in the Jupyter.
I created `config` manually. When I try to make the gym env, it failed.
Seems that your mujoco env is n…
-
Hi,
my model's info is as follows:
```
(encoder): Embedding(32, 100)
(lstm): LSTMCell(100, 100)
(_decoders): ModuleDict(
(attention_type): Linear(in_features=100, out_features=7, bias=T…
-
After last change added, the minimun ansible version required is 2.6.2
It is needed to use the vars/main/* files. This feature was added in ansible PR:
https://github.com/ansible/ansible/pull/36…
-
I am a bit confused in the implementation of maml_update and clone_module function. In maml_update first the gradient update is done for all parameters of model. Doesn't this mean that all submodules …
-
Hello,
I am trying to use the MTSAC algorithm on metaworld ML10. Is there already available trained params.pkl file that I could use to test the environment (in Pytorch) ?
-
Hello!
I've got a problem at initials state while importing potentials
`from maml.apps.pes import NNPotential
`
`ImportError: cannot import name 'NNPotential' from 'maml.apps.pes' (//anaconda3/li…
-
Hi,
I was trying to run the example of PES with GAP fitting, and would like to know how I can interface MAML code with GAP. I have installed quippy with GAP already but do not know how to let maml …
-
As per mentioned in paper, for MAML: 5 tasks are considered for 1 iteration. Each task contains 3 classes out of 9 subcategories and 6 images (3 for train and 3 for validation). However inside the cod…
-
Hello, author. I still don't understand. I can't find generate_ graphs_ britain, generate_ graphs_ by_ Where are these two functions? How to call it？looking forward to your reply
-
I wonder if the parallelization of n2p2 through mpi is transferred and can be used in the maml package.