decisionforce/EGPO
[CoRL 2021] Official implementation of paper "Safe Driving via Expert Guided Policy Optimization".
This project helps roboticists and autonomous vehicle developers train safer self-driving policies. It takes existing driving data and expert demonstrations to produce a refined control policy that avoids common pitfalls and dangerous situations. The primary user is a researcher or engineer working on motion planning and control for autonomous systems.
No commits in the last 6 months.
Use this if you need to train robust and safe autonomous driving policies using expert guidance to prevent unsafe actions.
Not ideal if you are looking for a general-purpose reinforcement learning library or if your primary focus is not on safety-critical autonomous navigation.
Stars
52
Forks
10
Language
Python
License
MIT
Category
Last pushed
Apr 08, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/decisionforce/EGPO"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/AirSim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI...
lgsvl/simulator
A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles
microsoft/AirSim-NeurIPS2019-Drone-Racing
Drone Racing @ NeurIPS 2019, built on Microsoft AirSim
DeepTecher/AutonomousVehiclePaper
无人驾驶相关论文速递
learn-to-race/l2r
Open-source reinforcement learning environment for autonomous racing — featured as a conference...