Robust Configuration of Evolutionary Algorithms. The purpose of this project is to develop an intelligent framework for the robust configuration of evolutionary algorithms. This research is driven by the fact that the current design of evolutionary algorithms is sub-optimal and ineffective for many problem domains. In the proposed framework, a configuration is evolved while the algorithm is running for problem solving to ensure robust design. Its scientific outcomes are expected to include a nov ....Robust Configuration of Evolutionary Algorithms. The purpose of this project is to develop an intelligent framework for the robust configuration of evolutionary algorithms. This research is driven by the fact that the current design of evolutionary algorithms is sub-optimal and ineffective for many problem domains. In the proposed framework, a configuration is evolved while the algorithm is running for problem solving to ensure robust design. Its scientific outcomes are expected to include a novel framework for the automated design of algorithms and new techniques for exploiting assumptions in algorithmic design that may have been overlooked. Expected practical outcomes include the provision of a robust problem-solving tool, strong research training and high-impact publications.Read moreRead less
Robust evolutionary analytics for changing and uncertain environments. This project aims to develop a novel framework for solving planning problems in dynamic environments with uncertainties. Current methods treat these conditions as two discrete problems. In the proposed framework, three algorithms will be developed and integrated to generate robust solutions for planning under dynamic changes with uncertainties. The intended outcomes include a novel framework with new techniques, developed by ....Robust evolutionary analytics for changing and uncertain environments. This project aims to develop a novel framework for solving planning problems in dynamic environments with uncertainties. Current methods treat these conditions as two discrete problems. In the proposed framework, three algorithms will be developed and integrated to generate robust solutions for planning under dynamic changes with uncertainties. The intended outcomes include a novel framework with new techniques, developed by exploiting the assumptions of existing methodologies. Practical outcomes will include a robust planning tool.Read moreRead less
Evolutionary Framework for High Dimensional Problems. The project aims to develop a novel framework for solving high dimensional decision problems with and without changes. This research is driven by the fact, that there is a huge gap between current research and the methodology needed to solve practical decision problems. In the proposed framework, a number of algorithms will be developed and integrated to generate robust solutions for those problems. The intended scientific outcomes include a ....Evolutionary Framework for High Dimensional Problems. The project aims to develop a novel framework for solving high dimensional decision problems with and without changes. This research is driven by the fact, that there is a huge gap between current research and the methodology needed to solve practical decision problems. In the proposed framework, a number of algorithms will be developed and integrated to generate robust solutions for those problems. The intended scientific outcomes include a novel framework with new techniques, developed by exploiting the impractical assumptions of existing methodologies. Practical outcomes include a robust decision-making tool and strong research training. The developed tool will provide significant cost savings through better decision making in practice.Read moreRead less
Reactive planning under disruptions and dynamic changes. This project aims to develop an algorithmic framework for reactive planning under unknown disturbances and dynamic changes. There is a huge gap between current research and the methodology needed to solve practical planning problems. The project will develop and integrate algorithms to ensure robust solutions for planning and re-planning under disruptions and dynamic changes. This project expects to develop an effective approach for solvin ....Reactive planning under disruptions and dynamic changes. This project aims to develop an algorithmic framework for reactive planning under unknown disturbances and dynamic changes. There is a huge gap between current research and the methodology needed to solve practical planning problems. The project will develop and integrate algorithms to ensure robust solutions for planning and re-planning under disruptions and dynamic changes. This project expects to develop an effective approach for solving complex decision problems, expand Australia’s knowledge base and research capability, and make it a leader in saving costs through better decision making.Read moreRead less
Smart Task Allocation Support for Small-Scale Printing Factory. The outcomes will give the Australian small-scale printing industry the capability to be competitive and cost-effective while looking after the wellbeing of its workforce. The understanding of complex relationships between various tasks in small-scale printing environments will improve the wellbeing of workers. The smart computer system will provide a frontier technology that will improve the profitability and efficiency. It will al ....Smart Task Allocation Support for Small-Scale Printing Factory. The outcomes will give the Australian small-scale printing industry the capability to be competitive and cost-effective while looking after the wellbeing of its workforce. The understanding of complex relationships between various tasks in small-scale printing environments will improve the wellbeing of workers. The smart computer system will provide a frontier technology that will improve the profitability and efficiency. It will also result in a cutting edge technology that is applicable to other similar industries.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE200101310
Funder
Australian Research Council
Funding Amount
$426,918.00
Summary
Dimension-reduced Reinforcement Learning for Large-scale Fleet Management. This project aims to address the problems in large-scale fleet management to ensure the efficiency of tomorrow’s transportation models, such as on-demand ride-hailing and mobility-as-a-service. The expected outcomes of this project include improved techniques for optimising the utility of large fleets of vehicles, and particularly robust dimension-reduced reinforcement learning algorithms that are capable of handling the ....Dimension-reduced Reinforcement Learning for Large-scale Fleet Management. This project aims to address the problems in large-scale fleet management to ensure the efficiency of tomorrow’s transportation models, such as on-demand ride-hailing and mobility-as-a-service. The expected outcomes of this project include improved techniques for optimising the utility of large fleets of vehicles, and particularly robust dimension-reduced reinforcement learning algorithms that are capable of handling the complex dynamics of supply and demand in transportation. The results should advance both research and technology in academia and the transportation industry and will also provide significant benefits to Australia and the international community by enhancing the energy-efficiency of and access to the mobility of the future.Read moreRead less