Gymnasium-Robotics

Gymnasium-Robotics copied to clipboard

[Bug Report] AdroitHandRelocate set env state is unstable when using states where the ball is being grasped.

4

If you are submitting a bug report, please fill in the following details and use the tag [bug]. **Describe the bug** It seems mujoco is a little unstable when it...

StoneT2000

[Proposal] MinariDataset Generation

1

### Proposal Up-to-date, re-runnable expert Minari datasets for offline learning. ### Motivation Minari is now at a stage where datasets can be made and uploaded for experimental use by others....

WillDudley

[Question] Algorithm / Parameters for Ant Maze

5

### Question I tried hard to train an agent to solve any of the AntMaze environments. I tried the stable baselines 3 implementations of SAC (dense and sparse) and PPO,...

meppe

[Question] Which of the MAMuJoCo environments are even "solvable"?

7

### Question **TL;DR: do you have baselines for performance on the environments using some popular MARL algorithm, say MADDPG or other?** Hi there, first of all, thanks for maintaining MAMuJoCo....

jcformanek

there are issues loading the franka model with mujoco==3.2.0

Kallinteris-Andreas

fixes https://github.com/Farama-Foundation/Gymnasium-Robotics/issues/222

Kallinteris-Andreas

The readme implies that the MaMuJoCo environments used to be part of D4RL; I don't believe that's the case.

jkterry1

Adroit hand dense reward fixes

3

* fix hand-to-object dense reward component sign in adroit hand door, hammer, and relocate scenarios # Description This PR fixes the hand-to-object dense reward component signs in the adroit hand...

7oponaut

[Bug Report] MazeEnv Goal Used is in i,j but should be x,y

2

If you are submitting a bug report, please fill in the following details and use the tag [bug]. **Describe the bug** The goal in generate_target_goal is selected from maze.unique_goal_locations which...

llewynS