Repository logo
 

Learning and policy search in stochastic dynamical systems with Bayesian neural networks

Published version
Peer-reviewed

Type

Conference Object

Change log

Authors

Depeweg, S 
Hernández-Lobato, JM 
Doshi-Velez, F 
Udluft, S 

Abstract

We present an algorithm for policy search in stochastic dynamical systems using model-based reinforcement learning. The system dynamics are described with Bayesian neural networks (BNNs) that include stochastic input variables. These input variables allow us to capture complex statistical patterns in the transition dynamics (e.g. multi-modality and heteroskedasticity), which are usually missed by alternative modeling approaches. After learning the dynamics, our BNNs are then fed into an algorithm that performs random roll-outs and uses stochastic optimization for policy learning. We train our BNNs by minimizing a-divergences with a = 0.5, which usually produces better results than other techniques such as variational Bayes. We illustrate the performance of our method by solving a challenging problem where model-based approaches usually fail and by obtaining promising results in real-world scenarios including the control of a gas turbine and an industrial benchmark.

Description

Keywords

Journal Title

5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings

Conference Name

International Conference on Learning Representations

Journal ISSN

Volume Title

Publisher

Rights

All rights reserved