Search Results for author: Mel Vecerik

Found 9 papers, 2 papers with code

Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings

no code implementations9 Dec 2021 Mel Vecerik, Jackie Kay, Raia Hadsell, Lourdes Agapito, Jon Scholz

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.

Keypoint Detection Object Tracking

Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study

no code implementations21 Mar 2021 Jianlan Luo, Oleg Sushkov, Rugile Pevceviciute, Wenzhao Lian, Chang Su, Mel Vecerik, Ning Ye, Stefan Schaal, Jon Scholz

In this paper we define criteria for industry-oriented DRL, and perform a thorough comparison according to these criteria of one family of learning approaches, DRL from demonstration, against a professional industrial integrator on the recently established NIST assembly benchmark.

S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency

no code implementations30 Sep 2020 Mel Vecerik, Jean-Baptiste Regli, Oleg Sushkov, David Barker, Rugile Pevceviciute, Thomas Rothörl, Christopher Schuster, Raia Hadsell, Lourdes Agapito, Jonathan Scholz

In this work we advocate semantic 3D keypoints as a visual representation, and present a semi-supervised training objective that can allow instance or category-level keypoints to be trained to 1-5 millimeter-accuracy with minimal supervision.

Image Reconstruction Representation Learning

Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient

no code implementations15 Nov 2019 Kevin Sebastian Luck, Mel Vecerik, Simon Stepputtis, Heni Ben Amor, Jonathan Scholz

This work evaluates the use of model-based trajectory optimization methods used for exploration in Deep Deterministic Policy Gradient when trained on a latent image embedding.

Continuous Control reinforcement-learning

Generative predecessor models for sample-efficient imitation learning

no code implementations ICLR 2019 Yannick Schroecker, Mel Vecerik, Jonathan Scholz

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 demonstrated states.

Imitation Learning

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

no code implementations2 Oct 2018 Mel Vecerik, Oleg Sushkov, David Barker, Thomas Rothörl, Todd Hester, Jon Scholz

Insertion is a challenging haptic and visual control problem with significant practical value for manufacturing.

Robotics

Sim-to-Real Robot Learning from Pixels with Progressive Nets

no code implementations13 Oct 2016 Andrei A. Rusu, Mel Vecerik, Thomas Rothörl, Nicolas Heess, Razvan Pascanu, Raia Hadsell

The progressive net approach is a general framework that enables reuse of everything from low-level visual features to high-level policies for transfer to new tasks, enabling a compositional, yet simple, approach to building complex skills.

reinforcement-learning

Cannot find the paper you are looking for? You can Submit a new open access paper.