Patrick Mannion
YOU?
Author Swipe
View article: Ireland in 2057: Projections using a Geographically Diverse Dynamic Microsimulation
Ireland in 2057: Projections using a Geographically Diverse Dynamic Microsimulation Open
This paper presents a dynamic microsimulation model developed for Ireland, designed to simulate key demographic processes and individual life-course transitions from 2022 to 2057. The model captures four primary events: births, deaths, int…
View article: A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Energy Management
A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Energy Management Open
Effective residential appliance scheduling is crucial for sustainable living. While multi-objective reinforcement learning (MORL) has proven effective in balancing user preferences in appliance scheduling, traditional MORL struggles with l…
View article: Learning in Multi-Objective Public Goods Games with Non-Linear Utilities
Learning in Multi-Objective Public Goods Games with Non-Linear Utilities Open
Addressing the question of how to achieve optimal decision-making under risk and uncertainty is crucial for enhancing the capabilities of artificial agents that collaborate with or support humans. In this work, we address this question in …
View article: Learning in Multi-Objective Public Goods Games with Non-Linear Utilities
Learning in Multi-Objective Public Goods Games with Non-Linear Utilities Open
Addressing the question of how to achieve optimal decision-making under risk and uncertainty is crucial for enhancing the capabilities of artificial agents that collaborate with or support humans. In this work, we address this question in …
View article: A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Environments
A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Environments Open
Effective residential appliance scheduling is crucial for sustainable living. While multi-objective reinforcement learning (MORL) has proven effective in balancing user preferences in appliance scheduling, traditional MORL struggles with l…
View article: Demonstration Guided Multi-Objective Reinforcement Learning
Demonstration Guided Multi-Objective Reinforcement Learning Open
Multi-objective reinforcement learning (MORL) is increasingly relevant due to its resemblance to real-world scenarios requiring trade-offs between multiple objectives. Catering to diverse user preferences, traditional reinforcement learnin…
View article: Low-cost Open-architecture Experimental Platform for Dynamic Systems and Feedback Control
Low-cost Open-architecture Experimental Platform for Dynamic Systems and Feedback Control Open
Traditional system dynamics and control systems learning platforms are costly, non-portable, and require substantial laboratory space. Consequently, these traditional systems must be shared amongst large groups of students, resulting in st…
View article: Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning
Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning Open
An important challenge in multi-objective reinforcement learning is obtaining a Pareto front of policies to attain optimal performance under different preferences. We introduce Iterated Pareto Referent Optimisation (IPRO), which decomposes…
View article: Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning
Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning Open
Research in multi-objective reinforcement learning (MORL) has introduced the utility-based paradigm, which makes use of both environmental rewards and a function that defines the utility derived by the user from those rewards. In this pape…
View article: Go-Explore for Residential Energy Management
Go-Explore for Residential Energy Management Open
Reinforcement learning is commonly applied in residential energy management, particularly for optimizing energy costs. However, RL agents often face challenges when dealing with deceptive and sparse rewards in the energy control domain, es…
View article: Inferring Preferences from Demonstrations in Multi-Objective Residential Energy Management
Inferring Preferences from Demonstrations in Multi-Objective Residential Energy Management Open
It is often challenging for a user to articulate their preferences accurately in multi-objective decision-making problems. Demonstration-based preference inference (DemoPI) is a promising approach to mitigate this problem. Understanding th…
View article: Distributional Multi-Objective Decision Making
Distributional Multi-Objective Decision Making Open
For effective decision support in scenarios with conflicting objectives, sets of potentially optimal solutions can be presented to the decision maker. We explore both what policies these sets should contain and how such sets can be compute…
View article: Know Your Enemy: Identifying Adversarial Behaviours in Deep Reinforcement Learning Agents (Student Abstract)
Know Your Enemy: Identifying Adversarial Behaviours in Deep Reinforcement Learning Agents (Student Abstract) Open
It has been shown that an agent can be trained with an adversarial policy which achieves high degrees of success against a state-of-the-art DRL victim despite taking unintuitive actions. This prompts the question: is this adversarial behav…
View article: Evolutionary Strategy Guided Reinforcement Learning via MultiBuffer Communication
Evolutionary Strategy Guided Reinforcement Learning via MultiBuffer Communication Open
Evolutionary Algorithms and Deep Reinforcement Learning have both successfully solved control problems across a variety of domains. Recently, algorithms have been proposed which combine these two methods, aiming to leverage the strengths a…
View article: Distributional Multi-Objective Decision Making
Distributional Multi-Objective Decision Making Open
For effective decision support in scenarios with conflicting objectives, sets of potentially optimal solutions can be presented to the decision maker. We explore both what policies these sets should contain and how such sets can be compute…
View article: Monte Carlo tree search algorithms for risk-aware and multi-objective reinforcement learning
Monte Carlo tree search algorithms for risk-aware and multi-objective reinforcement learning Open
In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from a single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For ex…
View article: Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning: A Dynamic Weight-based Approach
Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning: A Dynamic Weight-based Approach Open
Many decision-making problems feature multiple objectives. In such problems, it is not always possible to know the preferences of a decision-maker for different objectives. However, it is often possible to observe the behavior of decision-…
View article: SLA Doctoral Students' Collaborative Digital Storytelling Experiences and Perceptions
SLA Doctoral Students' Collaborative Digital Storytelling Experiences and Perceptions Open
Multiple studies in the field of teacher education have demonstrated the potential of digital storytelling to facilitate acquisition of teacher knowledge, critical examination of sociocultural or sociopolitical issues, and exploration and …
View article: Special issue on evolutionary machine learning
Special issue on evolutionary machine learning Open
An abstract is not available for this content. As you have access to this content, full HTML content is provided on this page. A PDF of this content is also available in through the ‘Save PDF’ action button.
View article: Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning
Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning Open
In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from a single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For ex…
View article: Multi-Objective Coordination Graphs for the Expected Scalarised Returns with Generative Flow Models
Multi-Objective Coordination Graphs for the Expected Scalarised Returns with Generative Flow Models Open
Many real-world problems contain multiple objectives and agents, where a trade-off exists between objectives. Key to solving such problems is to exploit sparse dependency structures that exist between agents. For example, in wind farm cont…
View article: A multi‐objective multi‐agent deep reinforcement learning approach to residential appliance scheduling
A multi‐objective multi‐agent deep reinforcement learning approach to residential appliance scheduling Open
Residential buildings are large consumers of energy. They contribute significantly to the demand placed on the grid, particularly during hours of peak demand. Demand‐side management is crucial to reducing this demand placed on the grid and…
View article: Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning
Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning Open
Infectious disease outbreaks can have a disruptive impact on public health and societal processes. As decision making in the context of epidemic mitigation is hard, reinforcement learning provides a methodology to automatically learn preve…