Search

Your search keyword '"Wu, Annie S."' showing total 163 results
Start Over Author "Wu, Annie S."
163 results on '"Wu, Annie S."'

1. Attention-Driven Multi-Agent Reinforcement Learning: Enhancing Decisions with Expertise-Informed Tasks

Author

Kuroswiski, Andre R, Wu, Annie S, and Passaro, Angelo

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Multiagent Systems
Abstract

In this paper, we introduce an alternative approach to enhancing Multi-Agent Reinforcement Learning (MARL) through the integration of domain knowledge and attention-based policy mechanisms. Our methodology focuses on the incorporation of domain-specific expertise into the learning process, which simplifies the development of collaborative behaviors. This approach aims to reduce the complexity and learning overhead typically associated with MARL by enabling agents to concentrate on essential aspects of complex tasks, thus optimizing the learning curve. The utilization of attention mechanisms plays a key role in our model. It allows for the effective processing of dynamic context data and nuanced agent interactions, leading to more refined decision-making. Applied in standard MARL scenarios, such as the Stanford Intelligent Systems Laboratory (SISL) Pursuit and Multi-Particle Environments (MPE) Simple Spread, our method has been shown to improve both learning efficiency and the effectiveness of collaborative behaviors. The results indicate that our attention-based approach can be a viable approach for improving the efficiency of MARL training process, integrating domain-specific knowledge at the action level., Comment: This paper was published at Proceedings of FLAIRS-37, May 19-21, Sandestin Beach, FL. The proceedings version is available at https://journals.flvc.org/FLAIRS/issue/view/6284

Published
2024

2. PID-inspired modifications in response threshold models in swarm intelligent systems

Author

Kebari, Maryam, Wu, Annie S., and Mathias, H. David

Subjects
Computer Science - Multiagent Systems
Abstract

In this study, we investigate the effectiveness of using the PID (Proportional - Integral - Derivative) control loop factors for modifying response thresholds in a decentralized, non-communicating, threshold-based swarm. Each agent in our swarm has a set of four thresholds, each corresponding to a task the agent is capable of performing. The agent will act on a particular task if the stimulus is higher than its corresponding threshold. The ability to modify their thresholds allows the agents to specialize dynamically in response to task demands. Current approaches to dynamic thresholds typically use a learning and forgetting process to adjust thresholds. These methods are able to effectively specialize once, but can have difficulty re-specializing if the task demands change. Our approach, inspired by the PID control loop, alters the threshold values based on the current task demand value, the change in task demand, and the cumulative sum of previous task demands. We show that our PID-inspired method is scalable and outperforms fixed and current learning and forgetting response thresholds with non-changing, constant, and abrupt changes in task demand. This superior performance is due to the ability of our method to re-specialize repeatedly in response to changing task demands., Comment: to be published in the Proceedings of the Genetic and Evolutionary Computation Conference 2023

Published
2023
Full Text
View/download PDF

3. Analysis of Evolved Response Thresholds for Decentralized Dynamic Task Allocation

Author

Mathias, H. David, Wu, Annie S., and Dang, Daniel

Subjects
Computer Science - Multiagent Systems
Abstract

We investigate the application of a multi-objective genetic algorithm to the problem of task allocation in a self-organizing, decentralized, threshold-based swarm. Each agent in our system is capable of performing four tasks with a response threshold for each, and we seek to assign response threshold values to all of the agents a swarm such that the collective behavior of the swarm is optimized. Random assignment of threshold values according to a uniform distribution is known to be effective; however, this method does not consider features of particular problem instances. Dynamic response thresholds have some flexibility to address problem specific features through real-time adaptivity, often improving swarm performance. In this work, we use a multi-objective genetic algorithm to evolve response thresholds for a simulated swarm engaged in a dynamic task allocation problem: two-dimensional collective tracking. We show that evolved thresholds not only outperform uniformly distributed thresholds and dynamic thresholds but achieve nearly optimal performance on a variety of tracking problem instances (target paths). More importantly, we demonstrate that thresholds evolved for one of several problem instances generalize to all other problem instances eliminating the need to evolve new thresholds for each problem to be solved. We analyze the properties that allow these paths to serve as universal training instances and show that they are quite natural., Comment: 22 pages, 12 figures

Published
2021

4. Genetic Algorithms For Extractive Summarization

Author

Chen, William, Ramos, Kensal, Mullaguri, Kalyan Naidu, and Wu, Annie S.

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

Most current work in NLP utilizes deep learning, which requires a lot of training data and computational power. This paper investigates the strengths of Genetic Algorithms (GAs) for extractive summarization, as we hypothesized that GAs could construct more efficient solutions for the summarization task due to their relative customizability relative to deep learning models. This is done by building a vocabulary set, the words of which are represented as an array of weights, and optimizing those set of weights with the GA. These weights can be used to build an overall weighting of a sentence, which can then be passed to some threshold for extraction. Our results showed that the GA was able to learn a weight representation that could filter out excessive vocabulary and thus dictate sentence importance based on common English words., Comment: 4 pages, 2 figures

Published
2021

8. Variable Response Duration Promotes Self-organization in Decentralized Swarms

Author

Engholdt, Kaelan, Mathias, H. David, Wu, Annie S., Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Filipič, Bogdan, editor, Minisci, Edmondo, editor, and Vasile, Massimiliano, editor

Published
2020
Full Text
View/download PDF

9. Dynamic Response Thresholds: Heterogeneous Ranges Allow Specialization While Mitigating Convergence to Sink States

Author

Wu, Annie S., Mathias, H. David, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Dorigo, Marco, editor, Stützle, Thomas, editor, Blesa, Maria J., editor, Blum, Christian, editor, Hamann, Heiko, editor, Heinrich, Mary Katherine, editor, and Strobel, Volker, editor

Published
2020
Full Text
View/download PDF

10. Heterogeneous Response Intensity Ranges and Response Probability Improve Goal Achievement in Multi-agent Systems

Author

Mathias, H. David, Wu, Annie S., Ruetten, Laik, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Dorigo, Marco, editor, Stützle, Thomas, editor, Blesa, Maria J., editor, Blum, Christian, editor, Hamann, Heiko, editor, Heinrich, Mary Katherine, editor, and Strobel, Volker, editor

Published
2020
Full Text
View/download PDF

13. Distributed Consensus Formation Through Unconstrained Gossiping

Author

Hollander, Christopher D. and Wu, Annie S.

Subjects
Computer Science - Systems and Control, Mathematics - Optimization and Control
Abstract

Gossip algorithms are widely used to solve the distributed consensus problem, but issues can arise when nodes receive multiple signals either at the same time or before they are able to finish processing their current work load. Specifically, a node may assume a new state that represents a linear combination of all received signals; even if such a state makes no sense in the problem domain. As a solution to this problem, we introduce the notion of conflict resolution for gossip algorithms and prove that their application leads to a valid consensus state when the underlying communication network possesses certain properties. We also introduce a methodology based on absorbing Markov chains for analyzing gossip algorithms that make use of these conflict resolution algorithms. This technique allows us to calculate both the probabilities of converging to a specific consensus state and the time that such convergence is expected to take. Finally, we make use of simulation to validate our methodology and explore the temporal behavior of gossip algorithms as the size of the network, the number of states per node, and the network density increase.

Published
2013

17. Genetically Engineered ART Architectures

Author

Al-Daraiseh, Ahmad, Kaylani, Assem, Georgiopoulos, Michael, Mollaghasemi, Mansooreh, Wu, Annie S., Anagnostopoulos, Georgios, Kacprzyk, Janusz, editor, Kaburlasos, Vassilis G., editor, and Ritter, Gerhard X., editor

Published
2007
Full Text
View/download PDF

18. Identification, Expansion, and Disambiguation of Acronyms in Biomedical Texts

Author

Bracewell, David B., Russell, Scott, Wu, Annie S., Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Chen, Guihai, editor, Pan, Yi, editor, Guo, Minyi, editor, and Lu, Jian, editor

Published
2005
Full Text
View/download PDF

20. Planning with Recursive Subgoals

Author

Yu, Han, Marinescu, Dan C., Wu, Annie S., Siegel, Howard Jay, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Negoita, Mircea Gh., editor, Howlett, Robert J., editor, and Jain, Lakhmi C., editor

Published
2004
Full Text
View/download PDF

21. Winnowing Wheat from Chaff: The Chunking GA

Author

Stringer, Hal, Wu, Annie S., Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, and Deb, Kalyanmoy, editor

Published
2004
Full Text
View/download PDF

22. Effects of Module Encapsulation in Repetitively Modular Genotypes on the Search Space

Author

Garibay, Ivan I., Garibay, Ozlem O., Wu, Annie S., Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, and Deb, Kalyanmoy, editor

Published
2004
Full Text
View/download PDF

24. Evolving Sensor Suites for Enemy Radar Detection

Author

Yilmaz, Ayse S., McQuay, Brian N., Yu, Han, Wu, Annie S., Sciortino, John C., Jr., Goos, Gerhard, editor, Hartmanis, Juris, editor, van Leeuwen, Jan, editor, Cantú-Paz, Erick, editor, Foster, James A., editor, Deb, Kalyanmoy, editor, Davis, Lawrence David, editor, Roy, Rajkumar, editor, O’Reilly, Una-May, editor, Beyer, Hans-Georg, editor, Standish, Russell, editor, Kendall, Graham, editor, Wilson, Stewart, editor, Harman, Mark, editor, Wegener, Joachim, editor, Dasgupta, Dipankar, editor, Potter, Mitch A., editor, Schultz, Alan C., editor, Dowsland, Kathryn A., editor, Jonoska, Natasha, editor, and Miller, Julian, editor

Published
2003
Full Text
View/download PDF

25. Adaptation of Length in a Nonstationary Environment

Author

Yu, Han, Wu, Annie S., Lin, Kuo-Chi, Schiavone, Guy, Goos, Gerhard, editor, Hartmanis, Juris, editor, van Leeuwen, Jan, editor, Cantú-Paz, Erick, editor, Foster, James A., editor, Deb, Kalyanmoy, editor, Davis, Lawrence David, editor, Roy, Rajkumar, editor, O’Reilly, Una-May, editor, Beyer, Hans-Georg, editor, Standish, Russell, editor, Kendall, Graham, editor, Wilson, Stewart, editor, Harman, Mark, editor, Wegener, Joachim, editor, Dasgupta, Dipankar, editor, Potter, Mitch A., editor, Schultz, Alan C., editor, Dowsland, Kathryn A., editor, Jonoska, Natasha, editor, and Miller, Julian, editor

Published
2003
Full Text
View/download PDF

28. Genome length as an evolutionary self-adaptation

Author

Ramsey, Connie Loggia, De Jong, Kenneth A., Grefenstettc, John J., Wu, Annie S., Burke, Donald S., Goos, G., editor, Hartmanis, J., editor, van Leeuwen, J., editor, Eiben, Agoston E., editor, Bäck, Thomas, editor, Schoenauer, Marc, editor, and Schwefel, Hans-Paul, editor

Published
1998
Full Text
View/download PDF

29. A survey of intron research in genetics

Author

Wu, Annie S., Lindsay, Robert K., Goos, G., editor, Hartmanis, J., editor, van Leeuwen, J., editor, Voigt, Hans-Michael, editor, Ebeling, Werner, editor, Rechenberg, Ingo, editor, and Schwefel, Hans-Paul, editor

Published
1996
Full Text
View/download PDF

33. A sustainable model for integrating current topics in machine learning research into the undergraduate curriculam

Author

Georgiopoulos, Michael, DeMara, Ronald F., Gonzalez, Avelino J., Wu, Annie s., Mollaghasemi, Manosooreh, Gelenbe, Erol, Kysilka, Marcella, Secretan, Jimmy, Sharma, Carthik A., and Alansour, Ayman J.

Subjects
Machine learning -- Evaluation, Curriculum planning -- Planning, Computer science -- Study and teaching, Universities and colleges -- Florida, Universities and colleges -- Curricula, Universities and colleges -- Management, Computer supported collaborative learning, Company business management, Company business planning, Business, Education, Electronics, Electronics and electrical industries, University of Central Florida -- Curricula, University of Central Florida -- Management
Published
2009

36. Genetic-based planning with recursive subgoals

Author

Yu, Han, Marinescu, Dan C., Wu, Annie S., and Siegel, Howard Jay

Subjects
Genetic algorithms -- Usage, Genetic algorithms -- Research, Planning -- Methods, Planning -- Research, Recursive functions -- Research, Computers and office automation industries, Science and technology
Abstract

Abstract--In this paper, we introduce an effective strategy for subgoal division and ordering based upon recursive subgoals and combine this strategy with a genetic-based planning approach. This strategy can be [...]

Published
2005

37. Populating Genomes in a Dynamic Grid

Author

Yu, Han, Jiang, Ning, Wu, Annie S., Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, and Deb, Kalyanmoy, editor

Published
2004
Full Text
View/download PDF

38. An incremental genetic algorithm approach to multiprocessor scheduling

Author

Wu, Annie S., Han Yu, Shiyuan Jin, Kuo-Chi Lin, and Schiavone, Guy

Subjects
Multiprocessors -- Analysis, Scheduling (Management) -- Analysis, Parallel processing -- Analysis, Parallel processing, Business, Computers, Electronics, Electronics and electrical industries
Abstract

A new genetic algorithm approach to solving multiprocessor systems' task scheduling problems is proposed. This approach has an increased fitness function and a problem representation that can be adapted and requires less problem specific information and no repair mechanisms.

Published
2004

39. Intelligent automated control of life support systems using proportional representations

Author

Wu, Annie S. and Garibay, Ivan I.

Subjects
Stochastic processes, Proportional representation, Gene expression, Resource allocation, Genetic algorithms
Abstract

Effective automatic control of Advanced Life Support Systems (ALSS) is a crucial component of space exploration. An ALSS is a coupled dynamical system which can be extremely sensitive and difficult to predict. As a result, such systems can be difficult to control using deliberative and deterministic methods. We investigate the performance of two machine learning algorithms, a genetic algorithm (GA) and a stochastic hill-climber (SH), on the problem of learning how to control an ALSS, and compare the impact of two different types of problem representations on the performance of both algorithms. We perform experiments on three ALSS optimization problems using five strategies with multiple variations of a proportional representation for a total of 120 experiments. Results indicate that although a proportional representation can effectively boost GA performance, it does not necessarily have the same effect on other algorithms such as SH. Results also support previous conclusions [23] that multivector control strategies are an effective method for control of coupled dynamical systems. Index Terms--Genetic algorithm (GA), life support system control, resource allocation, proportional genetic algorithm, gene expression, proportional representation, stochastic hill-climbing (SH).

Published
2004

40. A Genetic Algorithm as a Learning Method Based on Geometric Representations

Author

Holifield, Gregory A., Wu, Annie S., Goos, Gerhard, editor, Hartmanis, Juris, editor, van Leeuwen, Jan, editor, Cantú-Paz, Erick, editor, Foster, James A., editor, Deb, Kalyanmoy, editor, Davis, Lawrence David, editor, Roy, Rajkumar, editor, O’Reilly, Una-May, editor, Beyer, Hans-Georg, editor, Standish, Russell, editor, Kendall, Graham, editor, Wilson, Stewart, editor, Harman, Mark, editor, Wegener, Joachim, editor, Dasgupta, Dipankar, editor, Potter, Mitch A., editor, Schultz, Alan C., editor, Dowsland, Kathryn A., editor, Jonoska, Natasha, editor, and Miller, Julian, editor

Published
2003
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results