A collection of environments for autonomous driving and tactical decision-making tasks
An episode of one of the environments available in highway-env.
pip install --user git+https://github.com/eleurent/highway-env
import gym
import highway_env
env = gym.make("highway-v0")
done = False
while not done:
action = ... # Your agent code here
obs, reward, done, info = env.step(action)
env.render()Read the documentation online.
If you use the project in your work, please consider citing it with:
@misc{highway-env,
author = {Leurent, Edouard},
title = {An Environment for Autonomous Driving Decision-Making},
year = {2018},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/eleurent/highway-env}},
}List of publications & submissions using highway-env (please open a pull request to add missing entries):
- Approximate Robust Control of Uncertain Dynamical Systems (Dec 2018)
- Interval Prediction for Continuous-Time Systems with Parametric Uncertainties (Apr 2019)
- Practical Open-Loop Optimistic Planning (Apr 2019)
- α^α-Rank: Practically Scaling α-Rank through Stochastic Optimisation (Sep 2019)
- Social Attention for Autonomous Decision-Making in Dense Traffic (Nov 2019)
- Budgeted Reinforcement Learning in Continuous State Space (Dec 2019)
- Multi-View Reinforcement Learning (Dec 2019)
- Reinforcement learning for Dialogue Systems optimization with user adaptation (Dec 2019)
- Distributional Soft Actor Critic for Risk Sensitive Learning (Apr 2020)
- Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes (Jun 2020)
env = gym.make("highway-v0")In this task, the ego-vehicle is driving on a multilane highway populated with other vehicles. The agent's objective is to reach a high speed while avoiding collisions with neighbouring vehicles. Driving on the right side of the road is also rewarded.
The highway-v0 environment.
env = gym.make("merge-v0")In this task, the ego-vehicle starts on a main highway but soon approaches a road junction with incoming vehicles on the access ramp. The agent's objective is now to maintain a high speed while making room for the vehicles so that they can safely merge in the traffic.
The merge-v0 environment.
env = gym.make("roundabout-v0")In this task, the ego-vehicle if approaching a roundabout with flowing traffic. It will follow its planned route automatically, but has to handle lane changes and longitudinal control to pass the roundabout as fast as possible while avoiding collisions.
The roundabout-v0 environment.
env = gym.make("parking-v0")A goal-conditioned continuous control task in which the ego-vehicle must park in a given space with the appropriate heading.
The parking-v0 environment.
env = gym.make("intersection-v0")An intersection negotiation task with dense traffic.
The intersection-v0 environment.
Agents solving the highway-env environments are available in the rl-agents and stable-baselines repositories.
pip install --user git+https://github.com/eleurent/rl-agents
The DQN agent solving highway-v0.
This model-free value-based reinforcement learning agent performs Q-learning with function approximation, using a neural network to represent the state-action value function Q.
The DDPG agent solving parking-v0.
This model-free policy-based reinforcement learning agent is optimized directly by gradient ascent. It uses Hindsight Experience Replay to efficiently learn how to solve a goal-conditioned task.
The Value Iteration agent solving highway-v0.
The Value Iteration is only compatible with finite discrete MDPs, so the environment is first approximated by a finite-mdp environment using env.to_finite_mdp(). This simplified state representation describes the nearby traffic in terms of predicted Time-To-Collision (TTC) on each lane of the road. The transition model is simplistic and assumes that each vehicle will keep driving at a constant speed without changing lanes. This model bias can be a source of mistakes.
The agent then performs a Value Iteration to compute the corresponding optimal state-value function.
This agent leverages a transition and reward models to perform a stochastic tree search (Coulom, 2006) of the optimal trajectory. No particular assumption is required on the state representation or transition model.
The MCTS agent solving highway-v0.