Skip to content

A benchmark environment for fully cooperative human-AI performance.

License

Notifications You must be signed in to change notification settings

HIRO-group/overcooked_ai

 
 

Repository files navigation

Building from source 🔧

It is useful to setup a conda environment with Python 3.7 (virtualenv works too):

conda create -n mhri python=3.7
conda activate mhri

Clone the repo

git clone https://github.com/HIRO-group/overcooked_ai

Finally, use python setup-tools to locally install

pip install -e overcooked_ai/

Code Structure Overview 🗺

overcooked_ai_py contains:

mdp/:

  • overcooked_mdp.py: main Overcooked game logic
  • overcooked_env.py: environment classes built on top of the Overcooked mdp
  • layout_generator.py: functions to generate random layouts programmatically

agents/:

  • agent.py: location of agent classes
  • benchmarking.py: sample trajectories of agents (both trained and planners) and load various models

planning/:

  • planners.py: near-optimal agent planning logic
  • search.py: A* search and shortest path logic

About

A benchmark environment for fully cooperative human-AI performance.

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 70.8%
  • Jupyter Notebook 29.2%