-
## Why
The current APIs for the CAMI Store are described using markdown readme files in an example-based fashion. To facilitate easier exploration and exploitation of the API we want to switch to [Sw…
-
Hi there,
I just managed to build mlpack and was looking for the reinforcement learning executable. I noticed that there was no executable created for reinforcement learning. Could you provide me…
-
Hi,
I have some concerns on the evaluations used throughout this code repository.
PPO/TRPO
~~The evaluation uses the same trajectories as for training. However, you have a horizon which could…
-
I have run the following codes on my model, with all variable domain in "discrete".
I have in total 7 dimensions. Each dimension has about 7 freedoms.
batch_size = 3
num_cores = 1
opt = GPyO…
-
@zivy
Here is a simple doubt.
As we know registration optimization algorithm like Gradient Descent etc can end up to local maxima or minima because in registration we formulate non convex optimiz…
-
From 311 self-play games I generated so far, I counted 157 draws, 139 white wins, and 15 black wins. This strikes me as odd, considering that the first move advantage should be worth very little for a…
-
There is an error in how the Focus Area Groups presents as in the Admin its correct.
The UI has Focus Area: 1 etc for the Focus Area Group
This should not have Focus Area in the title.
Only Focus Ar…
-
Data captured in the standard template format will be ready for import during January 2017.
-
Consider adding schema.org/Exhibition as a subtype of Event. It would be for (typically long-running) museum (or gallery, edu etc.) exhibitions.
No special properties proposed at this point, but exa…
-
I run this code and found that the Q Value can't increase. I guess it was because there's no target Q network with fixed parameters.