-
Currently trying to add discrete actions via a GumbelSoftmax policy, will require a number of changes to shape handling in SAC agent.
WIP here:
https://github.com/rlgraph/rlgraph/tree/sac_learni…
-
I left it running for a few epochs, several times to ensure that it was not a fluke.
And SAC is collapsing to always choose the same action.
```
replay_buffer/size 210000…
-
**Describe the bug**
Hi, I'm working on GAIL.Providing my own trajectory just as in the cartpole or pendulum example. It works with DQN and PPO but when I try to use it with algorithms DDPG or SAC I …
ghost updated
5 years ago
-
I read the paper DIAYN just now, and can't understand how to train the DIAYN in an env with discrete actions, because SAC is for continuous env. But in the paper, some experiments are based on mountai…
-
I want to use sac in the gym environment, such as SpaceInvaders.
How to do it?
-
To get the model parameters for new appliances, I went through both the JSON file and the NIPS 2015 paper. Please correct me if I am wrong in explaining my points:
1. In section 5.2 of the paper, …
-
I believe I found a bug in QMCPack when using the complex version compiled for GPUs. The energies obtained with a DMC simulation in a periodic system with twists do not agree with the values obtained …
-
**[Original report](https://bitbucket.org/tkeller/prost/issue/26) by tkeller (Bitbucket: [557058:280236d3-4090-4dc9-9a03-b6e1425df4e7](https://bitbucket.org/557058:280236d3-4090-4dc9-9a03-b6e1425df4e7…
-
I tested godel on different hardware configurations and on one configuration the node always crashes at start:
```
[surface_blending_service-2] process has died [pid 26385, exit code -11, cmd /home/m…