🤖 The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation

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)

Assetto Corsa OpenAI Gym Environment

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

"Good Robot! Now Watch This!": Repurposing Reinforcement Learning for Task-to-Task Transfer; and “Good Robot!”: Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer

[IROS 2025] Human Demo Videos to Robot Action Plans

Integrating learning and task planning for robots with Keras, including simulation, real robot, and multiple dataset support.

A robot learning from demonstration framework that trains a recurrent neural network for autonomous task execution

Kernelized Movement Primitives (KMP)

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

Train a robot to see the environment and autonomously perform different tasks

Dynamic Motion Primitives

Code for the paper Continual Learning from Demonstration of Robotic Skills

An implementation of Deep Q-Learning from Demonstrations (DQfD) for playing Atari 2600 video games

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

[ICLR 2022 Spotlight] Code for Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration

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

A framework and method to jointly learn a (neural) control objective function and a time-warping function only from sparse demonstrations or waypoints.

Inverse optimal control from incomplete trajectory observations, proposing the concept of the recovery matrix which provides further insights into objective learning process.

Stable dynamical system (motion policy) learning using Euclideanizing flows

RAMPA: Robotic Augmented Reality for Machine Programming by Demonstration https://arxiv.org/abs/2410.13412

PyTorch code for TAPAS-GMM.

Combined Learning from Demonstration and Motion Planning

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

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

Learning second order dynamical system

This repository contains the source code for our paper: "Feedback-efficient Active Preference Learning for Socially Aware Robot Navigation", accepted to IROS-2022. For more details, please refer to our project website at https://sites.google.com/view/san-fapl.

[T-RO] Python implementation of PRobabilistically-Informed Motion Primitives (PRIMP)