Marcin Korecki
YOU?
Author Swipe
View article: Mycomobility: Analysis of human transport through a mycorrhizal analogy
Mycomobility: Analysis of human transport through a mycorrhizal analogy Open
The field of transportation research addresses the complexities of a particular sociotechnical system. Its usual focus is on human transportation systems, but non-human systems that effect transportation are also abundant in nature. This p…
View article: Overcoming the Price of Anarchy by Steering with Recommendations
Overcoming the Price of Anarchy by Steering with Recommendations Open
Varied real world systems such as transportation networks, supply chains and energy grids present coordination problems where many agents must learn to share resources. It is well known that the independent and selfish interactions of agen…
View article: LLM Voting: Human Choices and AI Collective Decision-Making
LLM Voting: Human Choices and AI Collective Decision-Making Open
This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns. Our methodology involved using a dataset from a human voting experim…
View article: The Man Behind the Curtain: Appropriating Fairness in AI
The Man Behind the Curtain: Appropriating Fairness in AI Open
Our goal in this paper is to establish a set of criteria for understanding the meaning and sources of attributing (un)fairness to AI algorithms. To do so, we first establish that (un)fairness, like other normative notions, can be understoo…
View article: Democratizing traffic control in smart cities
Democratizing traffic control in smart cities Open
To improve the performance of systems, optimization has been the prevailing approach in the past. However, the approach faces challenges when multiple goals shall be simultaneously achieved. For illustration, we study a multi-agent system,…
View article: Biospheric AI
Biospheric AI Open
The dominant paradigm in AI ethics and value alignment is highly anthropocentric. The focus of these disciplines is strictly on human values which limits the depth and breadth of their insights. Recently, attempts to expand to a sentientis…
View article: LLM Voting: Human Choices and AI Collective Decision Making
LLM Voting: Human Choices and AI Collective Decision Making Open
This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns. Our methodology involved using a dataset from a human voting experim…
View article: Dynamic value alignment through preference aggregation of multiple objectives
Dynamic value alignment through preference aggregation of multiple objectives Open
The development of ethical AI systems is currently geared toward setting objective functions that align with human objectives. However, finding such functions remains a research challenge, while in RL, setting rewards by hand is a fairly s…
View article: Deep Reinforcement Meta-Learning and Self-Organization in Complex Systems: Applications to Traffic Signal Control
Deep Reinforcement Meta-Learning and Self-Organization in Complex Systems: Applications to Traffic Signal Control Open
We studied the ability of deep reinforcement learning and self-organizing approaches to adapt to dynamic complex systems, using the applied example of traffic signal control in a simulated urban environment. We highlight the general limita…
View article: Democracy by Design: Perspectives for Digitally Assisted, Participatory Upgrades of Society
Democracy by Design: Perspectives for Digitally Assisted, Participatory Upgrades of Society Open
The technological revolution, particularly the availability of more data and more powerful computational tools, has led to the emergence of a new scientific field called "Computational Diplomacy". Our work tries to define its scope and foc…
View article: How Well Do Reinforcement Learning Approaches Cope With Disruptions? The Case of Traffic Signal Control
How Well Do Reinforcement Learning Approaches Cope With Disruptions? The Case of Traffic Signal Control Open
Data-driven and machine-learning-based methods are increasingly used in attempts to master the challenges of the world. But are they really the best approaches to manage complex dynamical systems? Our aim is to gain more insights into this…
View article: Analytically Guided Reinforcement Learning for Green It and Fluent Traffic
Analytically Guided Reinforcement Learning for Green It and Fluent Traffic Open
This study investigates various methods for autonomous traffic signal control. We look into different types of control methods, including fixed time, adaptive, analytic, and reinforcement learning approaches. Machine learning approaches ar…