-
### ❓ Question
Hello, I'm trying to solve the Frozenlake-v1 environment with is_slippery = True (non-deterministic) with the stable baselines 3 A2C algorithm. I can solve the 4x4 version but I can't …
-
Should not Reach hole reward be -1?
-
I am a beginner in RL and running env.render() doesn't open any environment window, please help.
environment_name = "CartPole-v1"
env = gym.make(environment_name)
episodes = 5
for episode in r…
-
My understanding is that most RL algorithms will focus on supporting gymnasium going forward and that will be the standard. Trying to get ray rllib or other RL libraries with gym environments is prett…
-
之前代码一直跑不起来，归其原因还是tensorflow tensorlayer gym版本的问题不对劲。现在终于跑起来了。分享一下用到关键的包的版本：
gym==0.20.0
h5py==3.1.0
hdf5==1.12.1
keras==2.9.0
kiwisolver==1.4.5
matplotlib==3.8.4
opencv==4.6.0
py…
-
I'm planning to do some testing with the newly released ray 2.3.0 and I noticed the pettingzoo example is 9 months old and still uses gym rather than gymnasium, both should probably be updated. Will c…
-
Hi,
Thanks for the great work. After installing the latest version (1.10.1), I get the following error:
```
A module that was compiled using NumPy 1.x cannot be run in
NumPy 2.0.2 as it may cra…
-
I watched your YT [video](https://www.youtube.com/watch?v=HQnPp9b7IOk), and got to the point needing to install [Box2D](https://github.com/pybox2d/pybox2d). However it seems outdated/broken, so how di…
-
**Describe the bug**
I am trying to use d3rlpy==2.6.0 and the kitchen dataset from d4rl. I have checked the issue #358 and use `d3rlpy install minari` to install minari. But there are still some bugs…
-
### Question
I want to add a graph to the observation space by
```
# Create NetworkX graph
G = nx.Graph()
# Add nodes (C-alpha atoms) with 320-dimensional zero embeddings
for _, ro…