We present a novel multi-objective optimization methodology built upon a multi-agent blackboard framework. This multi-agent blackboard system (MABS) synthesizes blackboard architectures, multi-agent environments, and optimization theory. The blackboard architecture creates the framework for initializing, storing, and solving a multi-objective optimization problem. Multiple agents allow for an optimization problem to be...
Knowledge compilation improves search-intensive problem-solvers that are easily specified but inefficient. One promising approach improves efficiency by constructing a database of problem-instance/best-action pairs that replace problem-solving search with efficient lookup. The database is constructed by reverse enumeration- expanding the complete search space backwards, from the terminal problem instances. This approach...
The thesis focuses on model-based approximation methods for reinforcement
learning with large scale applications such as combinatorial optimization problems.
First, the thesis proposes two new model-based methods to stablize the
value–function approximation for reinforcement learning. The first one is the
BFBP algorithm, a batch-like reinforcement learning process which iterates between...
Knowledge workers are struggling in the information flood. There is a growing interest in intelligent desktop environments that help knowledge workers organize their daily life. Intelligent desktop environments allow the desktop user to define a set of “activities” that characterize the user’s desktop work. These environments then attempt to identify...
Oxo-hydroxo Group 5 metal clusters are an untapped resource to study and advance aqueous solution processing of metal oxide thin films. The tetramethylammonium (TMA) hexatantalate salt (TMA6[H2Ta6O19]) yields dense Ta2O5 films (~95% of the bulk ß-Ta2O5 density) with atomically smooth surfaces (<4 Å root mean square surface roughness). This same...
End users develop more software than any other group of programmers, using software authoring devices such as e-mail filtering editors, by-demonstration macro builders, and spreadsheet environments. Despite this, there has been only a little research on finding ways to help these programmers with the dependability of the software they create....
This work is inspired by problems in natural resource management centered on the challenge of invasive species. Computing optimal management policies for maintaining ecosystem sustainable is challenging. Many ecosystem management problems can be formulated as MDP (Markov Decision Process) planning problems. In a simulator-defined MDP, the Markovian dynamics and rewards...
In this work, we study the problem of learning and improving policies for probabilistic planning problems. In the first part, we train neural network policies for probabilistic planning problems modeled as factored Markov decision problems. The objective is to train problem-specific neural networks via supervised learning to imitate the action...
Machine learning systems are generally trained offline using ground truth data that has been labeled by experts. However, these batch training methods are not a good fit for many applications, especially in the cases where complete ground truth data is not available for offline training. In addition, batch methods do...
A series of laboratory experiments were conducted to study the wave field in the inner lagoon excited by ‘long’ incident waves. Three cases were considered: Cases A, B and C presenting incident waves of wavelength with factors of 1, 2 and 2.5 times the width of the reef respectively. The...