Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient

Nov 15, 2019
Kevin Sebastian Luck, Mel Vecerik, Simon Stepputtis, Heni Ben Amor, Jonathan Scholz

* Accepted for IROS 2019 

  Access Model/Code and Paper
A Framework for Data-Driven Robotics

Sep 26, 2019
Serkan Cabi, Sergio Gómez Colmenarejo, Alexander Novikov, Ksenia Konyushkova, Scott Reed, Rae Jeong, Konrad Żołna, Yusuf Aytar, David Budden, Mel Vecerik, Oleg Sushkov, David Barker, Jonathan Scholz, Misha Denil, Nando de Freitas, Ziyu Wang


  Access Model/Code and Paper
Generative predecessor models for sample-efficient imitation learning

Apr 01, 2019
Yannick Schroecker, Mel Vecerik, Jonathan Scholz


  Access Model/Code and Paper
Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards

Oct 08, 2018
Mel Vecerik, Todd Hester, Jonathan Scholz, Fumin Wang, Olivier Pietquin, Bilal Piot, Nicolas Heess, Thomas Rothörl, Thomas Lampe, Martin Riedmiller


  Access Model/Code and Paper
A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning

Oct 08, 2018
Mel Vecerik, Oleg Sushkov, David Barker, Thomas Rothörl, Todd Hester, Jon Scholz


  Access Model/Code and Paper
Sim-to-Real Robot Learning from Pixels with Progressive Nets

May 22, 2018
Andrei A. Rusu, Mel Vecerik, Thomas Rothörl, Nicolas Heess, Razvan Pascanu, Raia Hadsell


  Access Model/Code and Paper