Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning

1 code implementation • 3 Mar 2025 • Adrià López Escoriza, Nicklas Hansen, Stone Tao, Tongzhou Mu, Hao Su

Long-horizon tasks in robotic manipulation present significant challenges in reinforcement learning (RL) due to the difficulty of designing dense reward functions and effectively exploring the expansive state-action space.

Reinforcement Learning (RL)

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

no code implementations • 18 Dec 2024 • Xiu Yuan, Tongzhou Mu, Stone Tao, Yunhao Fang, Mengke Zhang, Hao Su

Recent advancements in robot learning have used imitation learning with large models and extensive demonstrations to develop effective policies.

Diversity Imitation Learning +1

ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks

1 code implementation • 9 Dec 2024 • Arth Shukla, Stone Tao, Hao Su

High-quality benchmarks are the foundation for embodied AI research, enabling significant advancements in long-horizon navigation, manipulation and rearrangement tasks.

Imitation Learning Object Rearrangement +1

ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI

1 code implementation • 1 Oct 2024 • Stone Tao, Fanbo Xiang, Arth Shukla, Yuzhe Qin, Xander Hinrichsen, Xiaodi Yuan, Chen Bao, Xinsong Lin, Yulin Liu, Tse-kai Chan, Yuan Gao, Xuanlin Li, Tongzhou Mu, Nan Xiao, Arnav Gurha, Zhiao Huang, Roberto Calandra, Rui Chen, Shan Luo, Hao Su

We introduce and open source ManiSkill3, the fastest state-visual GPU parallelized robotics simulator with contact-rich physics targeting generalizable manipulation.

Imitation Learning Motion Planning +1

Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning

1 code implementation • 6 May 2024 • Stone Tao, Arth Shukla, Tse-kai Chan, Hao Su

A forward curriculum is then used to accelerate the training of the initial policy to perform well on the full initial state distribution of the task and improve demonstration and sample efficiency.

Reinforcement Learning (RL)

ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills

1 code implementation • 9 Feb 2023 • Jiayuan Gu, Fanbo Xiang, Xuanlin Li, Zhan Ling, Xiqiang Liu, Tongzhou Mu, Yihe Tang, Stone Tao, Xinyue Wei, Yunchao Yao, Xiaodi Yuan, Pengwei Xie, Zhiao Huang, Rui Chen, Hao Su

Generalizable manipulation skills, which can be composed to tackle long-horizon and complex daily chores, are one of the cornerstones of Embodied AI.

Imitation Learning Reinforcement Learning (RL) +1

Emergent collective intelligence from massive-agent cooperation and competition

1 code implementation • 4 Jan 2023 • HanMo Chen, Stone Tao, Jiaxin Chen, Weihan Shen, Xihui Li, Chenghui Yu, Sikai Cheng, Xiaolong Zhu, Xiu Li

Since these learned group strategies arise from individual decisions without an explicit coordination mechanism, we claim that artificial collective intelligence emerges from massive-agent cooperation and competition.

reinforcement-learning Reinforcement Learning +1

Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization

1 code implementation • 14 Oct 2022 • Stone Tao, Xiaochen Li, Tongzhou Mu, Zhiao Huang, Yuzhe Qin, Hao Su

In the abstract environment, complex dynamics such as physical manipulation are removed, making abstract trajectories easier to generate.

Few-Shot Imitation Learning Reinforcement Learning (RL)

ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations

3 code implementations • 30 Jul 2021 • Tongzhou Mu, Zhan Ling, Fanbo Xiang, Derek Yang, Xuanlin Li, Stone Tao, Zhiao Huang, Zhiwei Jia, Hao Su

Here we propose SAPIEN Manipulation Skill Benchmark (ManiSkill) to benchmark manipulation skills over diverse objects in a full-physics simulator.