Generate expert demonstrations; GAIL(Generative Adversarial Imitation Learning); IRL(Inverse Reinforcement Learning)

GAIL learning to imitate PPO playing CartPole.

This repository contains two new algorithms: KPIRL and KLA. KPIRL is a non-linear extension to Abbeel and Ng's Projection IRL algorithm (detailed in "Apprenticeship Learning via Inverse Reinforcement Learning"). KLA is an approximate RL algorithm designed to be used with KPIRL in large state-action spaces without any reward shaping. The algorithms have been published in "Human Apprenticeship Learning via Kernel-based Inverse Reinforcement Learning."

Inverse Reinforcement Learning Algorithm implementation with Python

UAV communication using apprenticeship learning via Inverse Reinforcement Learning (IRL)

Generative Adversial Imitation Learning (GAIL) an inverse reinforcement learning algorithm

Ride Rescue connects drivers needing roadside help with nearby volunteers. Users can request assistance for breakdowns or emergencies, and volunteers get real-time alerts. The platform’s location-based matching and messaging tools make help fast, reliable, and foster a supportive road safety community.