Multi-agent version of highway_env/intersection at https://github.com/eleurent/highway-env
git clone and cd into this directory, then pip install -e .
import gym
import highway_env
env = gym.make("intersection-multiagent-v0")
done = False
while not done:
action = ... # Your agent code here
obs, reward, done, info = env.step(action)
env.render()