Gymnasium-Robotics icon indicating copy to clipboard operation
Gymnasium-Robotics copied to clipboard

A collection of robotics simulation environments for reinforcement learning

Results 19 Gymnasium-Robotics issues
Sort by recently updated
recently updated
newest added

# Description The gymnasium API allows users to seed the environment on each reset to yield reproducible results. Running the environment with the same seed should always give the exact...

# Description I changed the way that temporary xmls are stored for the maze envs. I have used this change for training and it improves stability, without it my training...

# Description new `xml_file` argument adds the ability to load robot, that can be loaded with `gymnasium/mujoco` environments example with Skydio X2 drone: ```py env = gymnasium.make('AntMaze_UMaze-v4', xml_file="/home/master-andreas/gym/maze_new/mujoco_menagerie/skydio_x2/scene.xml", max_episode_steps=100, max_geom=100000)...

# Description Updated the dense reward of Maze environments from exp(-distance) to -distance Fixes #175 ## Type of change Please delete options that are not relevant. - [ ] Bug...

### Proposal see https://github.com/Farama-Foundation/Gymnasium/issues/993

**Describe the bug** The function `reset_mocap_welds` in [mujoco_utils.py](https://github.com/Farama-Foundation/Gymnasium-Robotics/blob/main/gymnasium_robotics/utils/mujoco_utils.py#L74) doesn't work properly. ```python def reset_mocap_welds(model, data): """Resets the mocap welds that we use for actuation.""" if model.nmocap > 0 and model.eq_data...

### Question Looking at the dense reward function for Maze Env: return np.exp(-np.linalg.norm(desired_goal - achieved_goal)) The agent seems to prefer sitting the ball as close as possible to the goal...

### Question Hi, I have a robotic arm and am controlling it using a mocap body and `mocap_set_actoin()` provided in `mujoco_utils`. What I am observing is that every time I...

good first issue

**Describe the bug** The gymnasium API allows users to seed the environment on each reset to yield reproducible results. Running the environment with the same seed should always give the...

### Proposal In AdroitHandPen, when the agent drops the pen, there is no way to recover, but the environment still does not terminate. The proposal, as in #111, is to...

enhancement
good first issue
help wanted