imitation

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

[ICLR 2018] TensorFlow code for zero-shot visual imitation by self-supervised exploration

[NeurIPS 2020] Official PyTorch Implementation of "Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis". NeurIPS 2020.

A collection of papers, codes and talks of visual imitation learning/imitation learning from video for robotics.

Scalable Bayesian Inverse Reinforcement Learning (ICLR 2021) by Alex J. Chan and Mihaela van der Schaar.

[CoRL 2025] Pretraining code for FLOWER VLA on OXE

(NeurIPS '22) LISA: Learning Interpretable Skill Abstractions - A framework for unsupervised skill learning using Imitation

This is an imitation of Netease Music Player which is a Universal Windows Platform program.Now it can play music through the folder you have chose,control music progress and volume.But something other cool animation,album image and lyric are not developed./这是一个模仿UWP版本网易云音乐的JavaFX程序，现在它可以根据选择的音乐文件夹播放音乐，控制播放的进度和声音，不过一些其它的好看动画、专辑图和歌词还没有开发完成。

A curated list of research papers and open-source software for movement primitives.

SOTA algorithms for imitation learning (LfD and LfO) - Ranking algorithms for imitation learning (TMLR 2023)

Stable-baselines3 based CrowdNavigation Simulator, It is based on 2d lidar scan.

Problem Statement: Developing A Software For Dubbing Videos.

MAD教程·模仿篇：仿动画基地2010秋季OP。

Very simple Pool game at early stage of development.

A modular, GPU-accelerated control system framework for AUV. Features Model Predictive Control (MPC) with CasADi, CUDA-based environment mapping, GPU-accelerated A* path planning, Fossen equations for marine vehicle dynamics, and supports imitation learning by distilling CasADi-based nonlinear MPC models into NN controllers.

A collection of hands-on notebooks focused on training AI agents using Reinforcement Learning and Imitation Learning. This repository is built around practical experiments, including training agents in games, testing different algorithms, and exploring real-world challenges like reward design, exploration, and stability.

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.

MMD shader that is specifically made for Animasa Miku model to imitate how it originally looked like in Animation:Master (A:M), before being ported to MMD

Code from "How useful is quantilization for mitigating specification-gaming?"

自定义view仿写即刻、Flipboard的cooooool的动画效果