Papers of the day   All papers

Regularized Hierarchical Policies for Compositional Transfer in Robotics

Comments

DeepMind: Data-efficiency is one of the principal challenges for applying reinforcement learning on physical systems. We use hierarchical models to strengthen transfer while mitigating negative interference - saving weeks of training time for physical robots. https://arxiv.org/abs/1906.11228 https://t.co/6ksuaagS7j

1 replies, 382 likes


Markus Wulfmeier: Proud to announce our recent work on compositional, hierarchical models to strengthen #transfer between related tasks while mitigating negative interference. We considerably improve #dataefficiency for reinforcement learning on physical #robots (reducing training time by weeks)

2 replies, 45 likes


Markus Wulfmeier 🏡: We'll be at the first virtual #RSS2020 later this year presenting RHPO ! Looking forward to many exciting conversations on transfer learning, multitask and obviously robots! @RSS_Foundation

0 replies, 6 likes


Markus Wulfmeier 🏡: We have worked hard and here is the updated version of our work on compositional transfer learning in #ReinforcementLearning! https://arxiv.org/abs/1906.11228 https://sites.google.com/corp/view/rhpo Thanks to all #RSS2020 (@RSS_Foundation ) reviewers for providing many helpful suggestions.

1 replies, 4 likes


Content

Found on Jun 27 2019 at https://arxiv.org/pdf/1906.11228.pdf

PDF content of a computer science paper: Regularized Hierarchical Policies for Compositional Transfer in Robotics