Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Scholz, Jonathan"'
Many robot manipulation tasks can be framed as geometric reasoning tasks, where an agent must be able to precisely manipulate an object into a position that satisfies the task from a set of initial conditions. Often, task success is defined based on
Externí odkaz:
http://arxiv.org/abs/2404.13478
Autor:
Scholz, Jonathan
With recent research advances, the dream of bringing domestic robots into our everyday lives has become more plausible than ever. Domestic robotics has grown dramatically in the past decade, with applications ranging from house cleaning to food servi
Externí odkaz:
http://hdl.handle.net/1853/54366
Autor:
Vecerik, Mel, Regli, Jean-Baptiste, Sushkov, Oleg, Barker, David, Pevceviciute, Rugile, Rothörl, Thomas, Schuster, Christopher, Hadsell, Raia, Agapito, Lourdes, Scholz, Jonathan
A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or usefulness
Externí odkaz:
http://arxiv.org/abs/2009.14711
Model-free reinforcement learning algorithms such as Deep Deterministic Policy Gradient (DDPG) often require additional exploration strategies, especially if the actor is of deterministic nature. This work evaluates the use of model-based trajectory
Externí odkaz:
http://arxiv.org/abs/1911.06833
Autor:
Cabi, Serkan, Colmenarejo, Sergio Gómez, Novikov, Alexander, Konyushkova, Ksenia, Reed, Scott, Jeong, Rae, Zolna, Konrad, Aytar, Yusuf, Budden, David, Vecerik, Mel, Sushkov, Oleg, Barker, David, Scholz, Jonathan, Denil, Misha, de Freitas, Nando, Wang, Ziyu
Publikováno v:
Robotics: Science and Systems Conference 2020
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions. We show how to apply this framework to accomplish three different object manipu
Externí odkaz:
http://arxiv.org/abs/1909.12200
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 probabil
Externí odkaz:
http://arxiv.org/abs/1904.01139
Autor:
Vecerik, Mel, Hester, Todd, Scholz, Jonathan, Wang, Fumin, Pietquin, Olivier, Piot, Bilal, Heess, Nicolas, Rothörl, Thomas, Lampe, Thomas, Riedmiller, Martin
We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards. We build upon the Deep Deterministic Policy Gradient (DDPG) algorithm to use demonstrations. Both demonstrations and actual interaction
Externí odkaz:
http://arxiv.org/abs/1707.08817
We propose position-velocity encoders (PVEs) which learn---without supervision---to encode images to positions and velocities of task-relevant objects. PVEs encode a single image into a low-dimensional position state and compute the velocity state fr
Externí odkaz:
http://arxiv.org/abs/1705.09805
Publikováno v:
Child Development, 2009 Jul 01. 80(4), 1197-1209.
Externí odkaz:
https://www.jstor.org/stable/25592061
Publikováno v:
In Neuropsychologia 2008 46(12):2949-2957