This repository contains the cleaned and updated environments from the paper Emergent Complexity via Multi-agent Competition.
(Original code by OpenAI here)
Use pip install -r requirements.txt
to install dependencies. If you haven't used MuJoCo before, please refer to the installation guide.
The code has been tested with the following dependencies:
- Python version 3.7
- OpenAI GYM version 0.20.0 with MuJoCo 2.00 support (use mujoco-py version 2.0.2)
- Tensorflow version 1.15.0
- Numpy version 1.20.0
After installing all dependencies, make sure gym works with support for MuJoCo environments.
Next install gym-compete
package as:
cd gym-compete
pip install -e .
Check install is successful by coming out of the directory and trying import gym_compete
in python console. Some users might require a sudo pip install
.
To see a demo of all environments (with untrained agents) do:
bash demo_tasks.sh all
To instead try a single environment use:
bash demo_tasks.sh <task>
where <task>
is one of: run-to-goal-humans
, run-to-goal-ants
, you-shall-not-pass
, sumo-ants
, sumo-humans
and kick-and-defend
A full list of videos can be found under /demos
run-to-goal-humans
run-to-goal-ants
you-shall-not-pass
sumo-ants
sumo-humans
kick-and-defend