-
**Describe the bug**
```
When using a train model in to predict it throws an error with the following stack trace
File "/.../stable_baselines/common/base_class.py", line 367, in predict
acti…
Kuldr updated
5 years ago
-
When attempting to train a DDPG agent in a Pendulum-v0 environment, I ran into this error:
`
Traceback (most recent call last):
File "/path/to/spinningup/spinup/utils/run_entrypoint.py", line 1…
-
I executed baseline for "Pendulum-v0", however it does not work well...
I also tried it with changing the number of hidden nodes in layers into [16, 16].
However, it didn't work well, either.
A…
-
### Describe the problem
Training using the Rllib Python API generates results and logs with the date (Y-m-d_H-M-S) as the default dir/file name prefix which makes it difficult to identify/track diff…
-
Here's a test to demonstrate this:
```python
def test_policy_for_continuous_action_space(self):
# state_space (NN is a simple single fc-layer relu network (2 units), random biases, ra…
-
If I take the DDPG example and add a dropout layer to either the actor or critic model, I get an AssertionError from Theano (but not Tensorflow):
```
Traceback (most recent call last):
File "dd…
-
During starting container I receive this error:
```
---Setting umask to 000---
---Xonotic not found!---
% Total % Received % Xferd Average Speed Time Time Time Current
…
-
I tried to install baselines into my working environment but the testing failed.
Working environment: Tensorflow 1.12.0, python 3.6, gym 0.10.9
Error information:
def test_noise_normal():
>…
-
### System information
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: RedHat 6
- **Ray installed from (source or binary)**: source
- **Ray version**: master
- **Python version*…
-
I am trying to use `aiomultiprocess` in my project which the simplified idea of current implementation is
```python
# pip install gym
import gym
import numpy as np
from multiprocessing import …