Garrett Thomas — accepted AI-conference papers

2023

PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining

Garrett Thomas, Ching-An Cheng, Ricky Loynd, Felipe Vieira Frujeri, Vibhav Vineet, Mihai Jalobeanu +1

CoRL 2023poster

A rich representation is key to general robotic manipulation, but existing approaches to representation learning require large amounts of multimodal demonstrations. In this work we propose PLEX, a transformer-based architecture that learns from a small amount of task-agnostic visuomotor trajectories…

Cited by 12 Source ↗Scholar ↗

2021

Safe Reinforcement Learning by Imagining the Near Future

Garrett Thomas, Yuping Luo, Tengyu Ma

NeurIPS 2021poster

Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where unsafe states can be avoided by planning ahead a short time into…

Cited by 94 Source ↗PDF ↗code ↗Scholar ↗

2020

MOPO: Model-based Offline Policy Optimization

Tianhe Yu, Garrett Thomas, Lantao Yu, Stefano Ermon, James Y Zou, Sergey Levine +2

NeurIPS 2020poster

Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a batch of previously collected data. This problem setting is compelling, because it offers the promise of utilizing large, diverse, previously collected datasets to acquire policies without any costly or da…

Cited by 999 Source ↗PDF ↗code ↗Scholar ↗

2020

Model-based Adversarial Meta-Reinforcement Learning

Zichuan Lin, Garrett Thomas, Guangwen Yang, Tengyu Ma

NeurIPS 2020poster

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution shift. When the test task distribution is different from the tra…

Cited by 64 Source ↗PDF ↗code ↗Scholar ↗

2018

Learning Robotic Assembly from CAD

Garrett Thomas, Melissa Chien, Aviv Tamar, Juan Aparicio Ojea, Pieter Abbeel

ICRA 2018poster

In this work, motivated by recent manufacturing trends, we investigate autonomous robotic assembly. Industrial assembly tasks require contact-rich manipulation skills, which are challenging to acquire using classical control and motion planning approaches. Consequently, robot controllers for assembl…

Cited by 198 Source ↗Scholar ↗

2017

Learning from the hindsight plan — Episodic MPC improvement

Aviv Tamar, Garrett Thomas, Tianhao Zhang, Sergey Levine, Pieter Abbeel

ICRA 2017poster

Model predictive control (MPC) is a popular control method that has proved effective for robotics, among other fields. MPC performs re-planning at every time step. Re-planning is done with a limited horizon per computational and real-time constraints and often also for robustness to potential model…

Cited by 83 Source ↗Scholar ↗

2016

Value Iteration Networks

Aviv Tamar, YI WU, Garrett Thomas, Sergey Levine, Pieter Abbeel

NeurIPS 2016oral

We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is…

Cited by 808 Source ↗PDF ↗code ↗Scholar ↗