-
I've seen this test failure a number of times now. E.g., https://amplab.cs.berkeley.edu/jenkins/job/Ray-PRB/4869/console.
```
+ docker run --rm --shm-size=10G --memory=10G bf861e97ff02bbc38f1ef169…
-
Potentially acrobot, according to Deisenroth's suggestion.
-
### System information
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: WSL Ubuntu 18.04
- **Ray installed from (source or binary)**: Source
- **Ray version**: 0.7.0.dev1
- **Python…
-
I'm trying to save and load a model multiple times to train on Colab, and I just want to make sure that when I call model.load, I'm using the same hyperparameters as well.
-
### System information
- **OS Platform and Distribution**: Ubuntu 16.04.5
- **Ray installed from (source or binary)**: Source
- **Ray version**: 0.7.4
- **Python version**: 3.7.3
- **Exact comman…
-
I am trying to run DDPG with the gym Pendulum-v0 environment. However I am getting this error:
> TypeError: The batch size of x must be equal to or less thanthe size of the previous state h.
**T…
-
Can't install in Linux.
Rust is installed. and while loading rust packages it shows the follow error:
> error[E0658]: use of unstable library feature 'result_map_or_else'
> --> /home/carlo…
-
### System information
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**:Ubuntu
- **Ray installed from (source or binary)**: pip
- **Ray version**:0.7.1
- **Python version**:3.5
-…
-
Checklist:
- [x] Parallelized training for experts (Adam finished this via #57).
- [x] Get good experts for Humanoid and Ant [which are not doing well right now](https://github.com/HumanCompatib…
-
The DDPG page in the [documentation](https://stable-baselines.readthedocs.io/en/master/modules/ddpg.html#custom-policy-network) says that the actor-critic custom networks can be defined with net_arch,…