gym-fetch 0.2.0

A goal-conditioned multitask suite for the fetch robot

Extended Taskset for the Fetch Robot

Installation

you can do:

pip install gym-fetch

Alternatively, you can clone this repo and install under development mode:

git clone <this repo>
cd <this repo>
pip install -e .

Environments

We extend existing Fetch environments from gym, with 7 new manipulation tasks. The gym.Fetch environment are much better engineered than the sawyer environments that metaworld uses. They are faster to initialize, and have a small (50 step) maximum episode length, making these environments faster to train on.

We might or might not need to extend the max_episode_steps on more complex tasks.

Reach-v2	Push-v2	PickPlace-v2	Slide-v2

For Up-To-Date Environments

All documentations are maintained in the https://github.com/geyang/gym_fetch/blob/master/specs folder, where each task set is one markdown file.

• original gym fetch tasks: https://github.com/geyang/gym_fetch/blob/master/specs/gym_fetch.md

• ``bin`` tasks: https://github.com/geyang/gym_fetch/blob/master/specs/bin.md

• ``bin_debug`` tasks: https://github.com/geyang/gym_fetch/blob/master/specs/bin_debug.md

• ``box`` tasks: https://github.com/geyang/gym_fetch/blob/master/specs/box.md

• ``drawer`` tasks: https://github.com/geyang/gym_fetch/blob/master/specs/drawer.md

The multi-task environments are still under development. They are located under

fetch
├── tasksets
    ├── box_block.md
    ├── box_block.py

Primitive Single Task Environments

The tasks involve a single primitive action such as open/closing a box, or a drawer. They do not additionally involve placing an object into the opened drawer or box. We include bin picking and placing because the bin does not require additional actions to open.

Box-open-v0	Box-close-v0	Bin-pick-v0	Bin-place-v0
Drawer-open-v0	Drawer-close-v0

Intermediate Task

These tasks additionally require placing the object inside an open drawer or box. We include the Bin-picking environment for completeness.

Name	Status
Bin-pick-v2	✅ done
Bin-place-v2	✅ done
Box-place-v2	✅ done
Box-pick-v2	✅ done
Drawer-place-v2	✅ done
Drawer-pick-v2	✅ done

Bin-pick-v0	Bin-place-v0	Box-pick-v0	Box-place-v0
Drawer-pick-v0	Drawer-place-v0

Multi-task Environments

These environments require significantly more memory due to the increasing complexity of contact detection and collision dynamics. These are also slower to run.

Name	Render
BoxBin-v2	✅ done
DrawerBin-v2	✅ done
BoxBinDrawer-v2	✅ done

BoxBin-v0	DrawerBin-v0	BoxBinDrawer-v0