no code implementations • 5 Apr 2024 • Junlin Lu, Patrick Mannion, Karl Mason
Multi-objective reinforcement learning (MORL) is increasingly relevant due to its resemblance to real-world scenarios requiring trade-offs between multiple objectives.
Multi-Objective Reinforcement Learning reinforcement-learning
no code implementations • 11 Feb 2024 • Willem Röpke, Mathieu Reymond, Patrick Mannion, Diederik M. Roijers, Ann Nowé, Roxana Rădulescu
A significant challenge in multi-objective reinforcement learning is obtaining a Pareto front of policies that attain optimal performance under different preferences.
Multi-Objective Reinforcement Learning reinforcement-learning
no code implementations • 5 Feb 2024 • Peter Vamplew, Cameron Foale, Conor F. Hayes, Patrick Mannion, Enda Howley, Richard Dazeley, Scott Johnson, Johan Källström, Gabriel Ramos, Roxana Rădulescu, Willem Röpke, Diederik M. Roijers
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.
Multi-Objective Reinforcement Learning reinforcement-learning
no code implementations • 15 Jan 2024 • Junlin Lu, Patrick Mannion, Karl Mason
It is often challenging for a user to articulate their preferences accurately in multi-objective decision-making problems.
no code implementations • 15 Jan 2024 • Junlin Lu, Patrick Mannion, Karl Mason
We use the Go-Explore algorithm to solve the cost-saving task in residential energy management problems and achieve an improvement of up to 19. 84\% compared to the well-known reinforcement learning algorithms.
no code implementations • 20 Jun 2023 • Adam Callaghan, Karl Mason, Patrick Mannion
Evolutionary Algorithms and Deep Reinforcement Learning have both successfully solved control problems across a variety of domains.
1 code implementation • 9 May 2023 • Willem Röpke, Conor F. Hayes, Patrick Mannion, Enda Howley, Ann Nowé, Diederik M. Roijers
For effective decision support in scenarios with conflicting objectives, sets of potentially optimal solutions can be presented to the decision maker.
no code implementations • 27 Apr 2023 • Junlin Lu, Patrick Mannion, Karl Mason
In such problems, it is not always possible to know the preferences of a decision-maker for different objectives.
no code implementations • 23 Nov 2022 • Conor F. Hayes, Mathieu Reymond, Diederik M. Roijers, Enda Howley, Patrick Mannion
Both algorithms outperform the state-of-the-art in multi-objective reinforcement learning for the expected utility of the returns.
Multi-Objective Reinforcement Learning reinforcement-learning +1
no code implementations • 1 Jul 2022 • Conor F. Hayes, Timothy Verstraeten, Diederik M. Roijers, Enda Howley, Patrick Mannion
In such settings a set of optimal policies must be computed.
no code implementations • 11 Apr 2022 • Mathieu Reymond, Conor F. Hayes, Lander Willem, Roxana Rădulescu, Steven Abrams, Diederik M. Roijers, Enda Howley, Patrick Mannion, Niel Hens, Ann Nowé, Pieter Libin
As decision making in the context of epidemic mitigation is hard, reinforcement learning provides a methodology to automatically learn prevention strategies in combination with complex epidemic models.
no code implementations • 2 Jun 2021 • Conor F. Hayes, Timothy Verstraeten, Diederik M. Roijers, Enda Howley, Patrick Mannion
In this case, to apply multi-objective reinforcement learning, the expected utility of the returns must be optimised.
1 code implementation • 17 Mar 2021 • Conor F. Hayes, Roxana Rădulescu, Eugenio Bargiacchi, Johan Källström, Matthew Macfarlane, Mathieu Reymond, Timothy Verstraeten, Luisa M. Zintgraf, Richard Dazeley, Fredrik Heintz, Enda Howley, Athirai A. Irissappane, Patrick Mannion, Ann Nowé, Gabriel Ramos, Marcello Restelli, Peter Vamplew, Diederik M. Roijers
Real-world decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives.
no code implementations • 1 Feb 2021 • Conor F. Hayes, Mathieu Reymond, Diederik M. Roijers, Enda Howley, Patrick Mannion
In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from the single execution of a policy.
1 code implementation • 28 Jan 2021 • David O'Callaghan, Patrick Mannion
In our work, we demonstrate empirically that the tunable agents framework allows easy adaption between cooperative and competitive behaviours in sequential social dilemmas without the need for retraining, allowing a single trained agent model to be adjusted to cater for a wide range of behaviours and opponent strategies.
Multi-Objective Reinforcement Learning reinforcement-learning
1 code implementation • 14 Nov 2020 • Roxana Rădulescu, Timothy Verstraeten, Yijie Zhang, Patrick Mannion, Diederik M. Roijers, Ann Nowé
We contribute novel actor-critic and policy gradient formulations to allow reinforcement learning of mixed strategies in this setting, along with extensions that incorporate opponent policy reconstruction and learning with opponent learning awareness (i. e., learning while considering the impact of one's policy when anticipating the opponent's learning step).
no code implementations • 2 Feb 2020 • B Ravi Kiran, Ibrahim Sobh, Victor Talpaert, Patrick Mannion, Ahmad A. Al Sallab, Senthil Yogamani, Patrick Pérez
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 high dimensional environments.
no code implementations • 17 Jan 2020 • Roxana Rădulescu, Patrick Mannion, Yijie Zhang, Diederik M. Roijers, Ann Nowé
In multi-objective multi-agent systems (MOMAS), agents explicitly consider the possible tradeoffs between conflicting objective functions.
no code implementations • 6 Sep 2019 • Roxana Rădulescu, Patrick Mannion, Diederik M. Roijers, Ann Nowé
We develop a new taxonomy which classifies multi-objective multi-agent decision making settings, on the basis of the reward structures, and which and how utility functions are applied.
no code implementations • 10 Feb 2019 • 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).
no code implementations • 6 Jan 2019 • Victor Talpaert, Ibrahim Sobh, B Ravi Kiran, Patrick Mannion, Senthil Yogamani, Ahmad El-Sallab, Patrick Perez
Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind's AlphaGo.