Kallinteris Andreas

The behavior is the same as the original repo when `agent_obsk=None`, it simply becomes a single agent environment, it was just missdocumented https://github.com/schroederdewitt/multiagent_mujoco/blob/b212ddd74b258e7cea006ff1d642b5ffada4b99d/multiagent_mujoco/mujoco_multi.py#L43 https://github.com/schroederdewitt/multiagent_mujoco/blob/b212ddd74b258e7cea006ff1d642b5ffada4b99d/multiagent_mujoco/mujoco_multi.py#L67

1. Can you provide an example of the behavior of `agent_obsk=None` when using the original implementation ``` >>> import gymnasium_robotics >>> from gymnasium_robotics import mamujoco_v1 >>> env = mamujoco_v1.parallel_env("Ant", "2x4",...

Gemini created code example: ```py import numpy as np from pycocotools import mask as maskUtils # 1. Create a sample binary mask. # In a real-world scenario, this would be...

I will give it a try, where should I put the tests?, also is it ok to add `pycocotools` requirement? (perhaps optional)

have you tried using the `default_camera_config` argument? (it is included in `v5` of the environments)

is the bug present for `render_mode="human"`

`render_mode=rgb_array` gives you the images with `env.render()` on every step, if you want to segment them you will have to do that yourself

@7oponaut We use the CONTRIBUTING.md, from gymnasium this change (reward function adjustment) requires a new version to be made (''AdroitHand*-v2''), this can be done by creating new files with the...

@7oponaut you are correct, the reward function was changed then without a version bump, which is a mistake, this should at least be documented (we likely remove those environment versions...

the camera being upside down might be a windows thing @Aoyama7Hai what OS are you using