Model-Based Reinforcement Learning via Meta-Policy Optimization

Ignasi Clavera
Ignasi Clavera
Jonas Rothfuss
Jonas Rothfuss
Yasuhiro Fujita
Yasuhiro Fujita

CoRL, pp. 617-629, 2018.

Cited by: 64|Bibtex|Views57
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic performance as model-free methods. We propose Model-Based Meta-Policy-Optimization (MB-MPO), an approa...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments