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

2016/05/23 by Depeweg, Stefan, Hernández-Lobato, José Miguel, Doshi-Velez, Finale +1 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1605.07127

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 α-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.

Cited by

• Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertainty

Related

• Bayes-Adaptive Deep Model-Based Policy Optimisation
• Fast Model-based Policy Search for Universal Policy Networks
• Reinforcement Learning Using Expectation Maximization Based Guided\n Policy Search for Stochastic Dynamics
• Augmented Bayesian Policy Search
• Gaussian Process Policy Optimization