Mel Vecerík

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 21

Top Topics

Reinforcement Learning

Top Venues

Robotics: Science and Systems

Publications

Ben Eisner, Yi Yang, Todor Davchev, Mel Vecerík, Jonathan Scholz, David Held
Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks. CoRR (2024)
Mel Vecerík, Carl Doersch, Yi Yang, Todor Davchev, Yusuf Aytar, Guangyao Zhou, Raia Hadsell, Lourdes Agapito, Jon Scholz
RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation. ICRA (2024)
Ben Eisner, Yi Yang, Todor Davchev, Mel Vecerík, Jonathan Scholz, David Held
Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks. ICLR (2024)
Carl Doersch, Yi Yang, Mel Vecerík, Dilara Gokay, Ankush Gupta, Yusuf Aytar, João Carreira, Andrew Zisserman
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement. ICCV (2023)
Carl Doersch, Yi Yang, Mel Vecerík, Dilara Gokay, Ankush Gupta, Yusuf Aytar, João Carreira, Andrew Zisserman
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement. CoRR (2023)
Mel Vecerík, Carl Doersch, Yi Yang, Todor Davchev, Yusuf Aytar, Guangyao Zhou, Raia Hadsell, Lourdes Agapito, Jon Scholz
RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation. CoRR (2023)
Mel Vecerík, Jackie Kay, Raia Hadsell, Lourdes Agapito, Jon Scholz
Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings. ICRA (2022)
Jianlan Luo, Oleg Sushkov, Rugile Pevceviciute, Wenzhao Lian, Chang Su, Mel Vecerík, Ning Ye, Stefan Schaal, Jonathan Scholz
Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study. Robotics: Science and Systems (2021)
Jianlan Luo, Oleg Sushkov, Rugile Pevceviciute, Wenzhao Lian, Chang Su, Mel Vecerík, Ning Ye, Stefan Schaal, Jonathan Scholz
Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study. CoRR (2021)
Mel Vecerík, Jackie Kay, Raia Hadsell, Lourdes Agapito, Jon Scholz
Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings. CoRR (2021)
Serkan Cabi, Sergio Gómez Colmenarejo, Alexander Novikov, Ksenia Konyushkova, Scott E. Reed, Rae Jeong, Konrad Zolna, Yusuf Aytar, David Budden, Mel Vecerík, Oleg Sushkov, David Barker, Jonathan Scholz, Misha Denil, Nando de Freitas, Ziyu Wang
Scaling data-driven robotics with reward sketching and batch reinforcement learning. Robotics: Science and Systems (2020)
Mel Vecerík, Jean-Baptiste Regli, Oleg Sushkov, David Barker, Rugile Pevceviciute, Thomas Rothörl, Christopher Schuster, Raia Hadsell, Lourdes Agapito, Jonathan Scholz
S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency. CoRR (2020)
Mel Vecerík, Jean-Baptiste Regli, Oleg Sushkov, David Barker, Rugile Pevceviciute, Thomas Rothörl, Raia Hadsell, Lourdes Agapito, Jonathan Scholz
S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency. CoRL (2020)
Kevin Sebastian Luck, Mel Vecerík, Simon Stepputtis, Heni Ben Amor, Jonathan Scholz
Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient. CoRR (2019)
Serkan Cabi, Sergio Gómez Colmenarejo, Alexander Novikov, Ksenia Konyushkova, Scott E. Reed, Rae Jeong, Konrad Zolna, Yusuf Aytar, David Budden, Mel Vecerík, Oleg Sushkov, David Barker, Jonathan Scholz, Misha Denil, Nando de Freitas, Ziyu Wang
A Framework for Data-Driven Robotics. CoRR (2019)
Kevin Sebastian Luck, Mel Vecerík, Simon Stepputtis, Heni Ben Amor, Jonathan Scholz
Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient. IROS (2019)
Yannick Schroecker, Mel Vecerík, Jonathan Scholz
Generative predecessor models for sample-efficient imitation learning. ICLR (Poster) (2019)
Mel Vecerík, Oleg Sushkov, David Barker, Thomas Rothörl, Todd Hester, Jonathan Scholz
A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning. ICRA (2019)
Yannick Schroecker, Mel Vecerík, Jonathan Scholz
Generative predecessor models for sample-efficient imitation learning. CoRR (2019)
Tobias Pohlen, Bilal Piot, Todd Hester, Mohammad Gheshlaghi Azar, Dan Horgan, David Budden, Gabriel Barth-Maron, Hado van Hasselt, John Quan, Mel Vecerík, Matteo Hessel, Rémi Munos, Olivier Pietquin
Observe and Look Further: Achieving Consistent Performance on Atari. CoRR (2018)
Mel Vecerík, Oleg Sushkov, David Barker, Thomas Rothörl, Todd Hester, Jonathan Scholz
A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning. CoRR (2018)