-
Dear @takuseno,
I am trying to export to onnx and I am getting the broadcasting error.
```
\lib\site-packages\torch\onnx\utils.py:341: UserWarning: Model has no forward function
warnings.war…
-
-
Dear Author, it's an honor to see your paper and code! I am a novice in this area and now I am trying to reproduce the effect of your experiment, but I have encountered some obstacles. In Half-Cheetah…
-
In your experiment, ROS melody is python2 and pytorch is python3?
-
**Important Note: We do not do technical support, nor consulting** and don't answer personal questions per email.
Please post your question on the [RL Discord](https://discord.com/invite/xhfNqQv), [R…
-
**Important Note: We do not do technical support, nor consulting** and don't answer personal questions per email.
Please post your question on the [RL Discord](https://discord.com/invite/xhfNqQv), [R…
-
````
def calculate_log_pi(log_stds, noises, actions):
gaussian_log_probs = (-0.5 * noises.pow(2) - log_stds).sum(
dim=-1, keepdim=True) - 0.5 * math.log(2 * math.pi) * log_stds.size(-1)…
-
**Important Note: We do not do technical support, nor consulting** and don't answer personal questions per email.
Please post your question on the [RL Discord](https://discord.com/invite/xhfNqQv), [R…
-
## Steps to reproduce
1. I tried to run MBPO on HumanoidTruncatedObsEnv with the default parameters in this repo but the final reward is around 180(seems like random policy and not work)
2. I…
-
Hello @abalakrishna123 @bthananjeyan
Thanks for sharing this repo. I read your paper [Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones](https://arxiv.org/pdf/2010.15920.pdf). T…