132 citations · 208 across the 17 of their papers we have counts for
19 papers
MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning
Florian Felten, Umut Ucak, Hicham Azmani +10
Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting object…
Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning
Peter Vamplew, Cameron Foale, Conor F. Hayes +9
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 u…
Evolutionary Strategy Guided Reinforcement Learning via MultiBuffer Communication
Adam Callaghan, Karl Mason, Patrick Mannion
Evolutionary Algorithms and Deep Reinforcement Learning have both successfully solved control problems across a variety of domains. Recently, algorithms have been proposed which co…
Distributional Multi-Objective Decision Making
Willem Röpke, Conor F. Hayes, Patrick Mannion +3
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…
Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning: A Dynamic Weight-based Approach
Junlin Lu, Patrick Mannion, Karl Mason
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…
Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning
Conor F. Hayes, Mathieu Reymond, Diederik M. Roijers +2
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…
Multi-Objective Coordination Graphs for the Expected Scalarised Returns with Generative Flow Models
Conor F. Hayes, Timothy Verstraeten, Diederik M. Roijers +2
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 structure…
Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning
Mathieu Reymond, Conor F. Hayes, Lander Willem +8
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 l…
Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)
Peter Vamplew, Benjamin J. Smith, Johan Kallstrom +9
The recent paper `"Reward is Enough" by Silver, Singh, Precup and Sutton posits that the concept of reward maximisation is sufficient to underpin all intelligence, both natural and…
Expected Scalarised Returns Dominance: A New Solution Concept for Multi-Objective Decision Making
Conor F. Hayes, Timothy Verstraeten, Diederik M. Roijers +2
In many real-world scenarios, the utility of a user is derived from the single execution of a policy. In this case, to apply multi-objective reinforcement learning, the expected ut…
A Practical Guide to Multi-Objective Reinforcement Learning and Planning
Conor F. Hayes, Roxana Rădulescu, Eugenio Bargiacchi +15
Real-world decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcemen…
Risk Aware and Multi-Objective Decision Making with Distributional Monte Carlo Tree Search
Conor F. Hayes, Mathieu Reymond, Diederik M. Roijers +2
In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from the single execution of a policy. In these settings, making decision…
Exploring the Impact of Tunable Agents in Sequential Social Dilemmas
David O'Callaghan, Patrick Mannion
When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed r…
Opponent Learning Awareness and Modelling in Multi-Objective Normal Form Games
Roxana Rădulescu, Timothy Verstraeten, Yijie Zhang +3
Many real-world multi-agent interactions consider multiple distinct criteria, i.e. the payoffs are multi-objective in nature. However, the same multi-objective payoff vector may le…
Deep Reinforcement Learning for Autonomous Driving: A Survey
B Ravi Kiran, Ibrahim Sobh, Victor Talpaert +4
With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in…
A utility-based analysis of equilibria in multi-objective normal form games
Roxana Rădulescu, Patrick Mannion, Yijie Zhang +2
In multi-objective multi-agent systems (MOMAS), agents explicitly consider the possible tradeoffs between conflicting objective functions. We argue that compromises between competi…
Multi-Objective Multi-Agent Decision Making: A Utility-based Analysis and Survey
Roxana Rădulescu, Patrick Mannion, Diederik M. Roijers +1
The majority of multi-agent system (MAS) implementations aim to optimise agents' policies with respect to a single objective, despite the fact that many real-world problem domains…
Vulnerable road user detection: state-of-the-art and open challenges
Patrick Mannion
Correctly identifying vulnerable road users (VRUs), e.g. cyclists and pedestrians, remains one of the most challenging environment perception tasks for autonomous vehicles (AVs). T…
Exploring applications of deep reinforcement learning for real-world autonomous driving systems
Victor Talpaert, Ibrahim Sobh, B Ravi Kiran +4
Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind's AlphaGo. It has been successfully deployed in comme…