Jon Scholz — accepted AI-conference papers

2025

DemoStart: Demonstration-Led Auto-Curriculum Applied to Sim-to-Real with Multi-Fingered Robots

Maria Bauzá, Jose Enriaue Chen, Valentin Dalibard, Nimrod Gileadi, Roland Hafner, Murilo F. Martins +10

ICRA 2025

We present DemoStart, a novel auto-curriculum reinforcement learning method capable of learning complex manipulation behaviors on an arm equipped with a three- fingered robotic hand, from only a sparse reward and a handful of demonstrations in simulation. Learning from simulation drastically reduces

Cited by 12 Source ↗Scholar ↗

2024

RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation

Mel Vecerik, Carl Doersch, Yi Yang, Todor Davchev, Yusuf Aytar, Guangyao Zhou +3

ICRA 2024poster

For robots to be useful outside labs and specialized factories we need a way to teach them new useful behaviors quickly. Current approaches lack either the generality to onboard new tasks without task-specific engineering, or else lack the data-efficiency to do so in an amount of time that enables p…

Cited by 45 Source ↗Scholar ↗

2023

Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation

Mohit Sharma, Claudio Fantacci, Yuxiang Zhou, Skanda Koppula, Nicolas Heess, Jon Scholz +1

ICLR 2023poster

Recent works have shown that large models pretrained on common visual learning tasks can provide useful representations for a wide range of specialized perception problems, as well as a variety of robotic manipulation tasks. While prior work on robotic manipulation has predominantly used frozen pre…

Cited by 33 Source ↗PDF ↗Scholar ↗

2022

Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings

Mel Vecerik, Jackie Kay, Raia Hadsell, Lourdes Agapito, Jon Scholz

ICRA 2022poster

Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint embeddings in a single forward pass, meaning the model is trained…

Cited by 3 Source ↗Scholar ↗

2022

Offline Meta-Reinforcement Learning for Industrial Insertion

Tony Z. Zhao, Jianlan Luo, Oleg Sushkov, Rugile Pevceviciute, Nicolas Heess, Jon Scholz +2

ICRA 2022poster

Reinforcement learning (RL) can in principle let robots automatically adapt to new tasks, but current RL methods require a large number of trials to accomplish this. In this paper, we tackle rapid adaptation to new tasks through the framework of meta-learning, which utilizes past tasks to learn to a…

Cited by 104 Source ↗Scholar ↗

2022

Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation

Todor Davchev, Oleg Olegovich Sushkov, Jean-Baptiste Regli, Stefan Schaal, Yusuf Aytar, Markus Wulfmeier +1

ICLR 2022poster

Complex sequential tasks in continuous-control settings often require agents to successfully traverse a set of ``narrow passages'' in their state space. Solving such tasks with a sparse reward in a sample-efficient manner poses a challenge to modern reinforcement learning (RL) due to the associated…

Cited by 19 Source ↗PDF ↗Scholar ↗

2019

A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning

Mel Vecerik, Oleg Sushkov, David Barker, Thomas Rothörl, Todd Hester, Jon Scholz

ICRA 2019poster

Insertion is a challenging haptic and visual control problem with significant practical value for manufacturing. Existing approaches in the model-based robotics community can be highly effective when task geometry is known, but are complex and cumbersome to implement, and must be tailored to each in…

Cited by 136 Source ↗Scholar ↗

2019

Generative predecessor models for sample-efficient imitation learning

Yannick Schroecker, Mel Vecerik, Jon Scholz

ICLR 2019poster

We propose Generative Predecessor Models for Imitation Learning (GPRIL), a novel imitation learning algorithm that matches the state-action distribution to the distribution observed in expert demonstrations, using generative models to reason probabilistically about alternative histories of demonstra…

Cited by 41 Source ↗PDF ↗Scholar ↗