-
### Proposal
Add support for environments with `Graph` observation spaces in `AsyncVectorEnv` in Gymnasium. Currently, `AsyncVectorEnv` assumes observations can be stacked in a typical array-like f…
-
### Proposal
Add support for environments with `Graph` observation spaces in `AsyncVectorEnv` in Gymnasium. Currently, `AsyncVectorEnv` assumes observations can be stacked in a typical array-like for…
-
### ❓ Question
I am trying to use stablebaselines3 to handle a graph-related problem. Graphs of different sizes will have different numbers of nodes and edges, resulting in different observation spac…
-
Hi,
Can you please explain what are you action and observation space ? Is it collective thrust and body rate ? Or individual rotor thrust ?
-
### 🐛 Bug
Using a Dict or Tuple observation space and a MultiDiscrete action space together causes PPO or A2C models to fail. If you swap either space to be a box the issue is resolved. The environme…
-
Hi,
I plan to use a motion dataset to train the Unitree G1 in IsaacLab. I noticed that the observation space for the joints contains 37 dimensions, but I couldn't find in the documentation which di…
-
Jeg foreslår følgende observation space:
Data på aktiv planet:
* BodyID 0-9 : Discrete(10)
* Polar position r,v : Box(low=np.array([0.0, 0.0]), high=np.array([BOARD_RADIUS, 2*pi]), dtype=np.…
-
I'm currently doing a project related to transferring control policies from simulator to simulator. This lead me to try to standardize action and observation spaces between brax and mujoco.
I imple…
-
Encountered the following error while running the `example_agent.py` file, How to pro…
-
state_dim = env.observation_space.shape[0]
action_dim = env.action_space.shape[0]
max_action = float(env.action_space.high[0])
parking-v0
env.observation_space.shape return none lead to erro…
izvvv updated
6 months ago