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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

• siemens/industrialbenchmark — marked official in Papers with Code; named in the paper
• siemens/policy_search_bb-alpha — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1605.07127")
get_code_for_paper("1605.07127")
have("1605.07127")

Connect an agent — have() is free.