-
Hi,
Thanks for your fantastic job and sharing.
I am wondering what is the meaning under the actor's sample() and mean()? I read your paper but didn't find any explanation.
Thanks in advance.
-
# Problem
Currently the optimisation can only adjust detector elements if a muon passes through them (and three other detector layers), however elements on the edges rarely have muons pass through …
-
Is it possible to provide a custom model to SAC from a configuration file such as the case for `model` parameter as follows:
```
# Model options for the Q network(s).
…
-
We were seeing actions outside of the range while using compute_action and compute_single_action.
python 3.9.7
ray 1.9.2
gym 0.18.3
numpy 1.21.2
```
from ray.rllib.utils.test_utils import …
-
Hi. Thanks for sharing your work.
Could I ask did you use augmentation in your method? Since I didn't find any implemented transformation in your implementation.
But in the appendix, you mentioned…
-
On calling network.create_variables() for my agent (using a DDPG agent), my GPU memory gets used 100% instantly and never clears up.
I can control it by using a virtual memory cap, but I need memory …
-
### My objective:
Train a DDPG agent that performs well in my costume environment.
### My implementation:
I try to achieve the objective via the following two steps.
**_step 1:_** Train DDPG ag…
-
https://github.com/rail-berkeley/softlearning/blob/46f14436f62465a02b99f431bbcf57a7fa0fd09d/softlearning/algorithms/sac.py#L254-L255
The implementation of the alpha loss seems to vary from the formul…
-
This is the current design that contains major decisions for the project. Additional future work and improvements that are not part of this design are listed in https://github.com/AndrejOrsula/drl_gra…
-
You can write and transform multiple methods on the same module, but it doesn't seem possible to share parameters between them without manually merging the two parameter FlatMappings. It's particularl…