Skip to content

A benchmark environment for fully cooperative human-AI performance. Forked from Main to modify for use in experiments ran at King's College London.

License

Notifications You must be signed in to change notification settings

Ptisni/overcooked_ai

 
 

Repository files navigation

MDP python tests overcooked-ai codecov PyPI version "Open Issues" GitHub issues by-label Downloads

Overcooked-AI 🧑‍🍳🤖

5 of the available layouts. New layouts are easy to hardcode or generate programmatically.

Introduction 🥘

Overcooked-AI is a benchmark environment for fully cooperative human-AI task performance, based on the wildly popular video game Overcooked.

The goal of the game is to deliver soups as fast as possible. Each soup requires placing up to 3 ingredients in a pot, waiting for the soup to cook, and then having an agent pick up the soup and delivering it. The agents should split up tasks on the fly and coordinate effectively in order to achieve high reward.

You can try out the game here (playing with some previously trained DRL agents). To play with your own trained agents using this interface, you can use this repo. To run human-AI experiments, check out this repo. You can find some human-human and human-AI gameplay data already collected here.

Check out this repo for the DRL implementations compatible with the environment and reproducible results to our paper: On the Utility of Learning about Humans for Human-AI Coordination (also see our blog post).

For simple usage of the environment, it's worthwhile considering using this environment wrapper.

Research Papers using Overcooked-AI 📑

Installation ☑️

Installing from PyPI 🗜

You can install the pre-compiled wheel file using pip.

pip install overcooked-ai

Note that PyPI releases are stable but infrequent. For the most up-to-date development features, build from source

Building from source 🔧

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

conda create -n overcooked_ai python=3.7
conda activate overcooked_ai

Clone the repo

git clone https://github.com/HumanCompatibleAI/overcooked_ai.git

Finally, use python setup-tools to locally install

pip install -e overcooked_ai/

Verifying Installation 📈

When building from source, you can verify the installation by running the Overcooked unit test suite. The following commands should all be run from the overcooked_ai project root directory:

python testing/overcooked_test.py

If you're thinking of using the planning code extensively, you should run the full testing suite that verifies all of the Overcooked accessory tools (this can take 5-10 mins):

python -m unittest discover -s testing/ -p "*_test.py"

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

Python Visualizations 🌠

One can adapt a version of this file in order to be able to play games in terminal graphics with custom-defined agents.

Further Issues and questions ❓

If you have issues or questions, don't hesitate to contact either Micah Carroll at mdc@berkeley.edu or Nathan Miller at nathan_miller23@berkeley.edu

About

A benchmark environment for fully cooperative human-AI performance. Forked from Main to modify for use in experiments ran at King's College London.

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 69.8%
  • Jupyter Notebook 30.2%