Refine
Year of publication
- 2014 (3) (remove)
Language
- English (3) (remove)
Has Fulltext
- yes (3)
Keywords
- Adaptive Schrittweite (1)
- Anpassung (1)
- Biogas (1)
- Biogas Plant (1)
- Board Games (1)
- Climate Change Adaptation (1)
- Co-Kriging (1)
- Disaster Risk Reduction (1)
- Extreme Events (1)
- Klimawandelanpassung (1)
- Klimaänderung (1)
- Kriging (1)
- Maschinelles Lernen (1)
- Modellierung (1)
- Modelllernen (1)
- Multi-fidelity (1)
- N-tuple Systems (1)
- Natural Hazards (1)
- Naturgefahr (1)
- Online Adaptation (1)
- Optimierung (1)
- Optimization (1)
- Reinforcement Learning (1)
- Resilience (1)
- Resilienz (1)
- Risikomanagement (1)
- Risk Management (1)
- Simulation (1)
- Surrogate Models (1)
- Temporal Difference Learning (TDL) (1)
- Verwundbarkeit (1)
- Vulnerability (1)
In facing recent natural and man-made disasters Disaster Risk Reduction (DRR) and Climate Change Adaption (CCA) calls for integrative thinking and learning across cultures, disciplines and institutions. In times of increasing complexity, insecurity and uncertainty thinking outside the box becomes essential. This first volume of “Integrative Risk and Security Research” presents related research contributions developed in the context of the 2013 DAAD Alumni Summer School "Coping with Disasters and Climate Extremes - Challenges & Cooperation Potential". It invites the reader to look beyond common perspectives of DRR and CCA and relates climate change and natural disasters with interdisciplinary and bottom-up policy making.
Learning board games by self-play has a long tradition in computational intelligence for games. Based on Tesauro’s seminal success with TD-Gammon in 1994, many successful agents use temporal difference learning today. But in order to be successful with temporal difference learning on game tasks, often a careful selection of features and a large number of training games is necessary. Even for board games of moderate complexity like Connect-4, we found in previous work that a very rich initial feature set and several millions of game plays are required. In this work we investigate different approaches of online-adaptable learning rates like Incremental Delta Bar Delta (IDBD) or Temporal Coherence Learning (TCL) whether they have the potential to speed up learning for such a complex task. We propose a new variant of TCL with geometric step size changes. We compare those algorithms with several other state-of-the-art learning rate adaptation algorithms and perform a case study on the sensitivity with respect to their meta parameters. We show that in this set of learning algorithms those with geometric step size changes outperform those other algorithms with constant step size changes. Algorithms with nonlinear output functions are slightly better than linear ones. Algorithms with geometric step size changes learn faster by a factor of 4 as compared to previously published results on the task Connect-4.
An essential task for operation and planning of biogas plants is the optimization of substrate feed mixtures. Optimizing the monetary gain requires the determination of the exact amounts of maize, manure, grass silage, and other substrates. Accurate simulation models are mandatory for this optimization, because the underlying chemical processes are very slow. The simulation models themselves may be time-consuming to evaluate, hence we show how to use surrogate-model-based approaches to optimize biogas plants efficiently. In detail, a Kriging surrogate is employed. To improve model quality of this surrogate, we integrate cheaply available data into the optimization process. Doing so, Multi-fidelity modeling methods like Co-Kriging are employed. Furthermore, a two-layered modeling approach is employed to avoid deterioration of model quality due to discontinuities in the search space. At the same time, the cheaply available data is shown to be very useful for initialization of the employed optimization algorithms. Overall, we show how biogas plants can be efficiently modeled using data-driven methods, avoiding discontinuities as well as including cheaply available data. The application of the derived surrogate models to an optimization process is shown to be very difficult, yet successful for a lower problem dimension.