Arunkumar Byravan
Arunkumar Byravan
Research Scientist, DeepMind
Vahvistettu sähköpostiosoite verkkotunnuksessa google.com - Kotisivu
Nimike
Viittaukset
Viittaukset
Vuosi
Se3-nets: Learning rigid body motion using deep neural networks
A Byravan, D Fox
2017 IEEE International Conference on Robotics and Automation (ICRA), 173-180, 2017
2162017
Functional gradient motion planning in reproducing kernel hilbert spaces
Z Marinho, A Dragan, A Byravan, B Boots, S Srinivasa, G Gordon
arXiv preprint arXiv:1601.03648, 2016
592016
Learning predictive models of a depth camera & manipulator from raw execution traces
B Boots, A Byravan, D Fox
2014 IEEE International Conference on Robotics and Automation (ICRA), 4021-4028, 2014
472014
Se3-pose-nets: Structured deep dynamics models for visuomotor control
A Byravan, F Leeb, F Meier, D Fox
2018 IEEE International Conference on Robotics and Automation (ICRA), 3339-3346, 2018
382018
Space-time functional gradient optimization for motion planning
A Byravan, B Boots, SS Srinivasa, D Fox
2014 IEEE International Conference on Robotics and Automation (ICRA), 6499-6506, 2014
312014
Se3-pose-nets: Structured deep dynamics models for visuomotor planning and control
A Byravan, F Leeb, F Meier, D Fox
arXiv preprint arXiv:1710.00489, 2017
292017
Graph-based inverse optimal control for robot manipulation
A Byravan, M Monfort, B Ziebart, B Boots, D Fox
Twenty-Fourth International Joint Conference on Artificial Intelligence, 2015
282015
Prospection: Interpretable plans from language by predicting the future
C Paxton, Y Bisk, J Thomason, A Byravan, D Foxl
2019 International Conference on Robotics and Automation (ICRA), 6942-6948, 2019
252019
Imagined value gradients: Model-based policy optimization with tranferable latent dynamics models
A Byravan, JT Springenberg, A Abdolmaleki, R Hafner, M Neunert, ...
Conference on Robot Learning, 566-589, 2020
202020
Local search for policy iteration in continuous control
JT Springenberg, N Heess, D Mankowitz, J Merel, A Byravan, ...
arXiv preprint arXiv:2010.05545, 2020
82020
Layered hybrid inverse optimal control for learning robot manipulation from demonstration
A Byravan, M Montfort, B Ziebart, B Boots, D Fox
NIPS workshop on autonomous learning robots. Citeseer, 2014
82014
2017 IEEE International Conference on Robotics and Automation (ICRA)
A Byravan, D Fox
52017
Representation matters: Improving perception and exploration for robotics
M Wulfmeier, A Byravan, T Hertweck, I Higgins, A Gupta, T Kulkarni, ...
2021 IEEE International Conference on Robotics and Automation (ICRA), 6512-6519, 2021
32021
Learning dynamics models for model predictive agents
M Lutter, L Hasenclever, A Byravan, G Dulac-Arnold, P Trochim, N Heess, ...
arXiv preprint arXiv:2109.14311, 2021
22021
Motion-Nets: 6D Tracking of Unknown Objects in Unseen Environments using RGB
F Leeb, A Byravan, D Fox
arXiv preprint arXiv:1910.13942, 2019
22019
Functional manifold projections in Deep-LEARCH
J Mainprice, A Byravan, D Kappler, D Fox, S Schaal, N Ratliff
NIPS Workshop Neurorobotics, 2016
22016
Evaluating model-based planning and planner amortization for continuous control
A Byravan, L Hasenclever, P Trochim, M Mirza, AD Ialongo, Y Tassa, ...
arXiv preprint arXiv:2110.03363, 2021
2021
Towards Real Robot Learning in the Wild: A Case Study in Bipedal Locomotion
M Bloesch, J Humplik, V Patraucean, R Hafner, T Haarnoja, A Byravan, ...
5th Annual Conference on Robot Learning, 2021
2021
Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes
AX Lee, CM Devin, Y Zhou, T Lampe, JT Springenberg, K Bousmalis, ...
5th Annual Conference on Robot Learning, 2021
2021
On Multi-objective Policy Optimization as a Tool for Reinforcement Learning
A Abdolmaleki, SH Huang, G Vezzani, B Shahriari, JT Springenberg, ...
arXiv preprint arXiv:2106.08199, 2021
2021
Järjestelmä ei voi suorittaa toimenpidettä nyt. Yritä myöhemmin uudelleen.
Artikkelit 1–20