-
Are there any demos that can illustrate the process of using MATD3 / MADDPG to process discrete actions?
-
Dear Ling-Pan,
I am writing to request an update to the OMAR benchmark code to include implementation for the discrete action space. Despite our best efforts, we have been unable to locate the nece…
-
I understand from #258 that there is randomness in the generated VQGAN code sequences because of Gumbel Softmax, but the different sequences nevertheless reconstruct to similar looking images. However…
-
in the train_vae script the kl_loss is set to zero via the weight parameter and also in my elaborate runs of experiments, I found that including the KL term does more harm than it helps. @karpathy als…
-
These functions can be found in [`mindspore.ops`](https://jax.readthedocs.io/en/latest/jax.numpy.html) namespace.
\_
>Please keep in mind that the proper way to link an issue to this list is t…
-
I've noticed that pyro.distributions.RelaxedOneHotCategorical tends to underflow pretty dramatically if you decrease the temperature below 0.3 or so with many categories. I've been adding a slight mod…
-
> Most frontends should be implemented in very few lines of code, with many only being a single line of code. Shortening a frontend might involve adding a new function to our Experimental API, or exte…
-
`
class TPS(M.Module):
def __init__(self, variant='dTPS'):
...
def forward(self, reserved, pruned, now_reserved_policy, now_pruned_policy):
...
B, N, _ = reserve…
-
## 🚀 Feature
Add PlackettLuce and RelaxedPlackettLuce distributions. It is a simple distribution over permutations.
## Motivation
For optimization over categorical/binary variables (i.e. variat…
-
As described in your paper, the Gumbel Softmax trick is applied to enable the back-propagation. The gradients must go through the sampled adjacency matrix to the edge predictor. However, your implemen…