Open Access. Powered by Scholars. Published by Universities.®
Operations Research, Systems Engineering and Industrial Engineering Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Algorithm (1)
- Bench-mark problems (1)
- D-Optimal (1)
- Design of experiments (1)
- Feature combination (1)
-
- Hierarchical reinforcement learning (1)
- Least squares multiple regression (1)
- Levels of abstraction (1)
- MAXQ (1)
- Model based approach (1)
- Model-based reinforcement learning (1)
- Problem characterization (1)
- R-MAX (1)
- Reinforcement learning (1)
- Robotic environments (1)
- Second order response model (1)
- Simulation (1)
- State-of-the-art algorithms (1)
- Publication
- Publication Type
Articles 1 - 2 of 2
Full-Text Articles in Operations Research, Systems Engineering and Industrial Engineering
A Predictor Analysis Framework For Surface Radiation Budget Reprocessing Using Design Of Experiments, Patricia Allison Quigley
A Predictor Analysis Framework For Surface Radiation Budget Reprocessing Using Design Of Experiments, Patricia Allison Quigley
Engineering Management & Systems Engineering Theses & Dissertations
Earth’s Radiation Budget (ERB) is an accounting of all incoming energy from the sun and outgoing energy reflected and radiated to space by earth’s surface and atmosphere. The National Aeronautics and Space Administration (NASA)/Global Energy and Water Cycle Experiment (GEWEX) Surface Radiation Budget (SRB) project produces and archives long-term datasets representative of this energy exchange system on a global scale. The data are comprised of the longwave and shortwave radiative components of the system and is algorithmically derived from satellite and atmospheric assimilation products, and acquired atmospheric data. It is stored as 3-hourly, daily, monthly/3-hourly, and monthly averages of 1°x1° …
An Efficient Approach To Model-Based Hierarchical Reinforcement Learning, Zhuoru Li, Akshay Narayan, Tze-Yun Leong
An Efficient Approach To Model-Based Hierarchical Reinforcement Learning, Zhuoru Li, Akshay Narayan, Tze-Yun Leong
Research Collection School Of Computing and Information Systems
We propose a model-based approach to hierarchical reinforcement learning that exploits shared knowledge and selective execution at different levels of abstraction, to efficiently solve large, complex problems. Our framework adopts a new transition dynamics learning algorithm that identifies the common action-feature combinations of the subtasks, and evaluates the subtask execution choices through simulation. The framework is sample efficient, and tolerates uncertain and incomplete problem characterization of the subtasks. We test the framework on common benchmark problems and complex simulated robotic environments. It compares favorably against the stateof-the-art algorithms, and scales well in very large problems.