Diffusion policy: Visuomotor policy learning via action diffusion

C Chi, Z Xu, S Feng, E Cousineau… - … Journal of Robotics …, 2023 - journals.sagepub.com
This paper introduces Diffusion Policy, a new way of generating robot behavior by
representing a robot's visuomotor policy as a conditional denoising diffusion process. We …

Scaling up and distilling down: Language-guided robot skill acquisition

H Ha, P Florence, S Song - Conference on Robot Learning, 2023 - proceedings.mlr.press
We present a framework for robot skill acquisition, which 1) efficiently scale up data
generation of language-labelled robot data and 2) effectively distills this data down into a …

Combo: Conservative offline model-based policy optimization

T Yu, A Kumar, R Rafailov… - Advances in neural …, 2021 - proceedings.neurips.cc
Abstract Model-based reinforcement learning (RL) algorithms, which learn a dynamics
model from logged experience and perform conservative planning under the learned model …

What matters in learning from offline human demonstrations for robot manipulation

A Mandlekar, D Xu, J Wong, S Nasiriany… - arxiv preprint arxiv …, 2021 - arxiv.org
Imitating human demonstrations is a promising approach to endow robots with various
manipulation capabilities. While recent advances have been made in imitation learning and …

Rambo-rl: Robust adversarial model-based offline reinforcement learning

M Rigter, B Lacerda, N Hawes - Advances in neural …, 2022 - proceedings.neurips.cc
Offline reinforcement learning (RL) aims to find performant policies from logged data without
further environment interaction. Model-based algorithms, which learn a model of the …

Accelerating reinforcement learning with learned skill priors

K Pertsch, Y Lee, J Lim - Conference on robot learning, 2021 - proceedings.mlr.press
Intelligent agents rely heavily on prior experience when learning a new task, yet most
modern reinforcement learning (RL) approaches learn every task from scratch. One …

Mimicplay: Long-horizon imitation learning by watching human play

C Wang, L Fan, J Sun, R Zhang, L Fei-Fei, D Xu… - arxiv preprint arxiv …, 2023 - arxiv.org
Imitation learning from human demonstrations is a promising paradigm for teaching robots
manipulation skills in the real world. However, learning complex long-horizon tasks often …

Viola: Imitation learning for vision-based manipulation with object proposal priors

Y Zhu, A Joshi, P Stone, Y Zhu - Conference on Robot …, 2023 - proceedings.mlr.press
We introduce VIOLA, an object-centric imitation learning approach to learning closed-loop
visuomotor policies for robot manipulation. Our approach constructs object-centric …

Xskill: Cross embodiment skill discovery

M Xu, Z Xu, C Chi, M Veloso… - Conference on Robot …, 2023 - proceedings.mlr.press
Human demonstration videos are a widely available data source for robot learning and an
intuitive user interface for expressing desired behavior. However, directly extracting …

Augmenting reinforcement learning with behavior primitives for diverse manipulation tasks

S Nasiriany, H Liu, Y Zhu - 2022 International Conference on …, 2022 - ieeexplore.ieee.org
Realistic manipulation tasks require a robot to interact with an environment with a prolonged
sequence of motor actions. While deep reinforcement learning methods have recently …