Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks

Code

• github.com/siemens/industrialbenchmark
  OfficialIn papertf★ 142
• github.com/siemens/policy_search_bb-alpha
  OfficialIn papernone★ 0

Abstract

We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing -divergences, allowing us to capture complicated statistical patterns in the transition dynamics, e.g. multi-modality and heteroskedasticity, which are usually missed by other common modeling approaches. We illustrate the performance of our method by solving a challenging benchmark where model-based approaches usually fail and by obtaining promising results in a real-world scenario for controlling a gas turbine.

Tasks

Reproductions