Popular GitHub Repositories for Learning From Demonstration

Implementation of Inverse Reinforcement Learning (IRL) algorithms in Python/Tensorflow. Deep MaxEnt, MaxEnt, LPIRL

Implementation of Inverse Reinforcement Learning Algorithm on a toy car in a 2D world problem, (Apprenticeship Learning via Inverse Reinforcement Learning Abbeel & Ng, 2004)

Implementation of the paper "Overcoming Exploration in Reinforcement Learning with Demonstrations" Nair et al. over the HER baselines from OpenAI

Assetto Corsa OpenAI Gym Environment

[CVPR 2025] Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning

REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer (ICML 2022 Long Oral)

Online Signal Temporal Logic (STL) Monte-Carlo Tree Search for Guided Imitation Learning

[ICRA 2024] Learning from Human Guidance: Uncertainty-aware deep reinforcement learning for autonomous driving.

Stable dynamical system (motion policy) learning using Euclideanizing flows

[NeurIPS 2022] Code for Enhanced Meta Reinforcement Learning using Demonstrations in Sparse Reward Environments

Implementation of the paper "Human-like Planning for Reaching in Cluttered Environments" (ICRA 2020)

INQUIRE: INteractive Querying for User-aware Informative REasoning

This repository hosts the physical robot code for ToolFlowNet. Published at CoRL '22.

This repository presents the code for the Elastic Fast Marching Learning (EFML) demonstration learning algorithm.

This is the official Implementation of "Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning"

In this repository, the code associated with the paper: "Segment, Compare and Learn: Creating Movement Libraries of Complex Task for Learning from Demonstration" is presented.

基于任务参数化高斯过程 (TPGP) 的多参考系技能从演示中学习

Codebase of paper "Improving Trust Estimation in Human-Robot Collaboration Using Beta Reputation at Fine-grained Timescales" under review ?

code for the HAI paper "Give Me an Example Like This": Episodic Active Reinforcement Learning from Demonstrations