Follow
Isac Arnekvist
Isac Arnekvist
PhD student at Royal Institute of Technology (KTH), Sweden
Verified email at kth.se
Title
Cited by
Cited by
Year
Vpe: Variational policy embedding for transfer reinforcement learning
I Arnekvist, D Kragic, JA Stork
2019 International Conference on Robotics and Automation (ICRA), 36-42, 2019
342019
The effect of target normalization and momentum on dying relu
I Arnekvist, JF Carvalho, D Kragic, JA Stork
arXiv preprint arXiv:2005.06195, 2020
102020
Learning manipulation states and actions for efficient non-prehensile rearrangement planning
JA Haustein, I Arnekvist, J Stork, K Hang, D Kragic
arXiv preprint arXiv:1901.03557, 2019
102019
Non-prehensile rearrangement planning with learned manipulation states and actions
JA Haustein, I Arnekvist, J Stork, K Hang, D Kragic
Workshop" Machine Learning in Robot Motion Planning" at International …, 2018
22018
Transfer Learning using low-dimensional Representations in Reinforcement Learning
I Arnekvist
KTH Royal Institute of Technology, 2020
2020
[Re] Learning to Learn By Self-Critique
I Arnekvist, D Kalpakchi
arXiv preprint arXiv:1912.00183, 2019
2019
Reinforcement learning for robotic manipulation
I Arnekvist
2017
Finding competitors using Latent Dirichlet Allocation
I Arnekvist, L Ericson
2016
Hälsoarbetares prevention av HIV i Gambia
I Arnekvist, S Flemming
2010
Reinforcement Learning för manipulering med robot
I Arnekvist
The system can't perform the operation now. Try again later.
Articles 1–10