https://github.com/millionintegrals/vel-miniworld
An example project using vel to train reinforcement learning agents on existing community gym environments. A work in progress repository.
https://github.com/millionintegrals/vel-miniworld
Last synced: about 1 year ago
JSON representation
An example project using vel to train reinforcement learning agents on existing community gym environments. A work in progress repository.
- Host: GitHub
- URL: https://github.com/millionintegrals/vel-miniworld
- Owner: MillionIntegrals
- License: mit
- Created: 2018-11-23T23:05:07.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2018-11-25T08:47:09.000Z (over 7 years ago)
- Last Synced: 2025-03-24T07:22:27.903Z (over 1 year ago)
- Language: Python
- Homepage:
- Size: 5.47 MB
- Stars: 4
- Watchers: 1
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# vel-miniworld
An example project using vel to train reinforcement learning agents
on existing community gym environments. A work-in-progress repository.
Supported environments:
- https://github.com/maximecb/gym-minigrid
- https://github.com/maximecb/gym-miniworld
Examples confirmed to be working:
- `examples-configs/ppo/ppo_minigrid_empty_8x8.yaml`
- `examples-configs/ppo/ppo_minigrid_doorkey_6x6.yaml` (doesn't converge every time)
- `examples-configs/ppo/ppo_miniworld_hallway.yaml`
## How to run?
```bash
git clone git@github.com:MillionIntegrals/vel-miniworld.git
cd vel-miniworld
# Optionally, if you don't want to store metrics in the db and visualize in VisDom
mv .velproject.dummy.yaml .velproject.yaml
pipenv install
pipenv shell
vel examples-configs/ppo/ppo_minigrid_empty_8x8.yaml train
vel examples-configs/ppo/ppo_minigrid_empty_8x8.yaml record
# Optionally, play a video of agent solving a rather simple environment
mplayer output/videos/ppo_minigrid_empty_8x8/0/ppo_minigrid_empty_8x8_vid_0010.avi
```
## Additional notes
For the textures to load properly for the 3D rendered `miniworld` environment, it needs to be installed
from a git repository, by running `pip install -e .` in the top-level directory of the checkout.
Let me know if you have any other problems running the environments.
## Some animations
Solving simple small gridworld environment:
Solving slightly more complex gridworld environment with sparse rewards:
Solving small 3D rendered world:
