-
🔵 **Describe the bug:**
If I switch from single target to aoe talents I gain mulitshot on my hunter. But the ability wont fire. I need to go into the aoe macro and click update talents then save to g…
-
-
Hello I am trying to implement this type of method (VPG specifically from A. Zeng et al) on a real robot, however with UR robots with updated firmware the code/models as written by A. Zeng et al canno…
-
It's becoming a bit difficult to keep track of all the models already, it might be easier if for each model run we have a json file with all the important information. For example:
```
vpg_runs.json…
-
Because when they run our model on the server they will use 50 runs for 5 *different seeds*, I suggest that we re-evaluate the best trained models for each hyperparameters in this way. I also suggest …
-
My initial implementation of the VPG tooks around 300 sec to excute 200,000 environment interations.
It's about 2x slower than OpenAI Spinning Up implementation.
ran this with cProfile module.
``…
-
Hello
I'm not able to login to SSH with private key.
Terminal login works fine: `ssh sshuser@10.19.19.1 -i /home/sshuser/.ssh/sshuser`
But when I try to login via phpseclib it fails with error me…
-
**Describe the bug**
Directly observed:
```
seeing the log messages:
+ virt…
-
The value loss is increasing while training compared to OpenAI Spinning Up implementation.
the current implementation is increasing from 178 to 451, whileSpinning Up's value loss is decreasing from…
-
Refer https://github.com/yamatokataoka/reinforcement-learning-replications/issues/59