Browse Source

Update bibliography

master
Markus Kaiser 5 months ago
parent
commit
dd72d549bc
1 changed files with 13 additions and 6 deletions
  1. 13
    6
      zotero_export.bib

+ 13
- 6
zotero_export.bib View File

@@ -94,29 +94,36 @@
}

@article{depeweg_learning_2016,
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 alpha-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.},
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 α-divergences with α = 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.},
archivePrefix = {arXiv},
author = {Depeweg, Stefan and Hernández-Lobato, José Miguel and Doshi-Velez, Finale and Udluft, Steffen},
date = {2016-05-23},
eprint = {1605.07127},
eprinttype = {arxiv},
keywords = {Computer Science - Learning,Statistics - Machine Learning},
keywords = {Computer Science - Learning,Computer Science - Machine Learning,Statistics - Machine Learning},
langid = {english},
primaryClass = {cs, stat},
title = {Learning and {{Policy Search}} in {{Stochastic Dynamical Systems}} with {{Bayesian Neural Networks}}},
url = {http://arxiv.org/abs/1605.07127},
urldate = {2016-06-06}
urldate = {2019-02-19}
}

@inproceedings{hein_benchmark_2017,
abstract = {In the research area of reinforcement learning (RL), frequently novel and promising methods are developed and introduced to the RL community. However, although many researchers are keen to apply their methods on real-world problems, implementing such methods in real industry environments often is a frustrating and tedious process. Generally, academic research groups have only limited access to real industrial data and applications. For this reason, new methods are usually developed, evaluated and compared by using artificial software benchmarks. On one hand, these benchmarks are designed to provide interpretable RL training scenarios and detailed insight into the learning process of the method on hand. On the other hand, they usually do not share much similarity with industrial real-world applications. For this reason we used our industry experience to design a benchmark which bridges the gap between freely available, documented, and motivated artificial benchmarks and properties of real industrial problems. The resulting industrial benchmark (IB) has been made publicly available to the RL community by publishing its Java and Python code, including an OpenAI Gym wrapper, on Github. In this paper we motivate and describe in detail the IB's dynamics and identify prototypic experimental settings that capture common situations in real-world industry control problems.},
author = {Hein, D. and Depeweg, S. and Tokic, M. and Udluft, S. and Hentschel, A. and Runkler, T. A. and Sterzing, V.},
abstract = {In the research area of reinforcement learning (RL), frequently novel and promising methods are developed and introduced to the RL community. However, although many researchers are keen to apply their methods on real-world problems, implementing such methods in real industry environments often is a frustrating and tedious process. Generally, academic research groups have only limited access to real industrial data and applications. For this reason, new methods are usually developed, evaluated and compared by using articial software benchmarks. On one hand, these benchmarks are designed to provide interpretable RL training scenarios and detailed insight into the learning process of the method on hand. On the other hand, they usually do not share much similarity with industrial real-world applications. For this reason we used our industry experience to design a benchmark which bridges the gap between freely available, documented, and motivated articial benchmarks and properties of real industrial problems. The resulting industrial benchmark (IB) has been made publicly available to the RL community by publishing its Java and Python code, including an OpenAI Gym wrapper, on Github. In this paper we motivate and describe in detail the IBs dynamics and identify prototypic experimental settings that capture common situations in real-world industry control problems.},
author = {Hein, Daniel and Depeweg, Stefan and Tokic, Michel and Udluft, Steffen and Hentschel, Alexander and Runkler, Thomas A. and Sterzing, Volkmar},
booktitle = {2017 {{IEEE Symposium Series}} on {{Computational Intelligence}} ({{SSCI}})},
date = {2017-11},
doi = {10.1109/SSCI.2017.8280935},
eventtitle = {2017 {{IEEE Symposium Series}} on {{Computational Intelligence}} ({{SSCI}})},
isbn = {978-1-5386-2726-6},
keywords = {academic research groups,artificial software benchmarks,Automobiles,benchmark environment,Benchmark testing,frustrating process,Games,Helicopters,industrial control,Industrial control,industrial data,Industries,industry environments,industry experience,interpretable RL training scenarios,learning (artificial intelligence),learning process,motivated artificial benchmarks,public domain software,real-world applications,real-world industry control problems,reinforcement learning,research area,RL community,tedious process,Wind turbines},
langid = {english},
location = {{Honolulu, HI}},
pages = {1-8},
title = {A Benchmark Environment Motivated by Industrial Control Problems}
publisher = {{IEEE}},
title = {A Benchmark Environment Motivated by Industrial Control Problems},
url = {http://ieeexplore.ieee.org/document/8280935/},
urldate = {2019-02-19}
}

@inproceedings{hensman_gaussian_2013,

Loading…
Cancel
Save