Learning Fast Adaptation with Meta Strategy Optimization

Wenhao Yu
Wenhao Yu
Jie Tan
Jie Tan

international conference on robotics and automation, pp. 1-1, 2020.

Cited by: 2|Bibtex|Views38|DOI:https://doi.org/10.1109/lra.2020.2974685
Other Links: academic.microsoft.com|arxiv.org

Abstract:

The ability to walk in new scenarios is a key milestone on the path toward real-world applications of legged robots. In this work, we introduce Meta Strategy Optimization, a meta-learning algorithm for training policies with latent variable inputs that can quickly adapt to new scenarios with a handful of trials in the target environment...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments