Search Results for author: Arunkumar Byravan

Found 11 papers, 1 papers with code

Learning Dynamics Models for Model Predictive Agents

no code implementations29 Sep 2021 Michael Lutter, Leonard Hasenclever, Arunkumar Byravan, Gabriel Dulac-Arnold, Piotr Trochim, Nicolas Heess, Josh Merel, Yuval Tassa

This paper sets out to disambiguate the role of different design choices for learning dynamics models, by comparing their performance to planning with a ground-truth model -- the simulator.

Model-based Reinforcement Learning

Representation Matters: Improving Perception and Exploration for Robotics

no code implementations3 Nov 2020 Markus Wulfmeier, Arunkumar Byravan, Tim Hertweck, Irina Higgins, Ankush Gupta, tejas kulkarni, Malcolm Reynolds, Denis Teplyashin, Roland Hafner, Thomas Lampe, Martin Riedmiller

Furthermore, the value of each representation is evaluated in terms of three properties: dimensionality, observability and disentanglement.

Local Search for Policy Iteration in Continuous Control

no code implementations12 Oct 2020 Jost Tobias Springenberg, Nicolas Heess, Daniel Mankowitz, Josh Merel, Arunkumar Byravan, Abbas Abdolmaleki, Jackie Kay, Jonas Degrave, Julian Schrittwieser, Yuval Tassa, Jonas Buchli, Dan Belov, Martin Riedmiller

We demonstrate that additional computation spent on model-based policy improvement during learning can improve data efficiency, and confirm that model-based policy improvement during action selection can also be beneficial.

Continuous Control

Motion-Nets: 6D Tracking of Unknown Objects in Unseen Environments using RGB

no code implementations30 Oct 2019 Felix Leeb, Arunkumar Byravan, Dieter Fox

In this work, we bridge the gap between recent pose estimation and tracking work to develop a powerful method for robots to track objects in their surroundings.

Pose Estimation Translation

Prospection: Interpretable Plans From Language By Predicting the Future

no code implementations20 Mar 2019 Chris Paxton, Yonatan Bisk, Jesse Thomason, Arunkumar Byravan, Dieter Fox

High-level human instructions often correspond to behaviors with multiple implicit steps.

SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control

no code implementations2 Oct 2017 Arunkumar Byravan, Felix Leeb, Franziska Meier, Dieter Fox

In this work, we present an approach to deep visuomotor control using structured deep dynamics models.

SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks

no code implementations8 Jun 2016 Arunkumar Byravan, Dieter Fox

We introduce SE3-Nets, which are deep neural networks designed to model and learn rigid body motion from raw point cloud data.

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