Search Results for author: Ann Nowé

Found 44 papers, 20 papers with code

Dynamic Weights in Multi-Objective Deep Reinforcement Learning

3 code implementations20 Sep 2018 Axel Abels, Diederik M. Roijers, Tom Lenaerts, Ann Nowé, Denis Steckelmacher

In the dynamic weights setting the relative importance changes over time and specialized algorithms that deal with such change, such as a tabular Reinforcement Learning (RL) algorithm by Natarajan and Tadepalli (2005), are required.

Multi-Objective Reinforcement Learning reinforcement-learning

A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning

2 code implementations Conference on Neural Information Processing Systems Datasets and Benchmarks Track 2023 Florian Felten, Lucas N. Alegre, Ann Nowé, Ana L. C. Bazzan, El-Ghazali Talbi, Grégoire Danoy, Bruno C. da Silva

Multi-objective reinforcement learning algorithms (MORL) extend standard reinforcement learning (RL) to scenarios where agents must optimize multiple---potentially conflicting---objectives, each represented by a distinct reward function.

Benchmarking Multi-Objective Reinforcement Learning +1

Pareto Conditioned Networks

1 code implementation11 Apr 2022 Mathieu Reymond, Eugenio Bargiacchi, Ann Nowé

In multi-objective optimization, learning all the policies that reach Pareto-efficient solutions is an expensive process.

Multi-Objective Reinforcement Learning

Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization

1 code implementation18 Jan 2023 Lucas N. Alegre, Ana L. C. Bazzan, Diederik M. Roijers, Ann Nowé, Bruno C. da Silva

Finally, we introduce a bound that characterizes the maximum utility loss (with respect to the optimal solution) incurred by the partial solutions computed by our method throughout learning.

Active Learning Multi-Objective Reinforcement Learning

Ordered Preference Elicitation Strategies for Supporting Multi-Objective Decision Making

1 code implementation21 Feb 2018 Luisa M. Zintgraf, Diederik M. Roijers, Sjoerd Linders, Catholijn M. Jonker, Ann Nowé

We build on previous work on Gaussian processes and pairwise comparisons for preference modelling, extend it to the multi-objective decision support scenario, and propose new ordered preference elicitation strategies based on ranking and clustering.

Clustering Decision Making +1

Deep reinforcement learning for large-scale epidemic control

1 code implementation30 Mar 2020 Pieter Libin, Arno Moonens, Timothy Verstraeten, Fabian Perez-Sanjines, Niel Hens, Philippe Lemey, Ann Nowé

For this reason, we investigate a deep reinforcement learning approach to automatically learn prevention strategies in the context of pandemic influenza.

Computational Efficiency reinforcement-learning +1

Multi-Agent Thompson Sampling for Bandit Applications with Sparse Neighbourhood Structures

1 code implementation22 Nov 2019 Timothy Verstraeten, Eugenio Bargiacchi, Pieter JK Libin, Jan Helsen, Diederik M. Roijers, Ann Nowé

In this task, wind turbines must coordinate their alignments with respect to the incoming wind vector in order to optimize power production.

Thompson Sampling

Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (Technical Report)

1 code implementation17 Dec 2021 Florent Delgrange, Ann Nowé, Guillermo A. Pérez

Finally, we show how one can use a policy obtained via state-of-the-art RL to efficiently train a variational autoencoder that yields a discrete latent model with provably approximately correct bisimulation guarantees.

Reinforcement Learning (RL)

Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees

1 code implementation22 Mar 2023 Florent Delgrange, Ann Nowé, Guillermo A. Pérez

Our approach yields bisimulation guarantees while learning the distilled policy, allowing concrete optimization of the abstraction and representation model quality.

Opponent Learning Awareness and Modelling in Multi-Objective Normal Form Games

1 code implementation14 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).

Preference Communication in Multi-Objective Normal-Form Games

1 code implementation17 Nov 2021 Willem Röpke, Diederik M. Roijers, Ann Nowé, Roxana Rădulescu

We consider preference communication in two-player multi-objective normal-form games.

Evaluating COVID-19 vaccine allocation policies using Bayesian $m$-top exploration

1 code implementation30 Jan 2023 Alexandra Cimpean, Timothy Verstraeten, Lander Willem, Niel Hens, Ann Nowé, Pieter Libin

$m$-top exploration allows the algorithm to learn $m$ policies for which it expects the highest utility, enabling experts to inspect this small set of alternative strategies, along with their quantified uncertainty.

Bayesian Best-Arm Identification for Selecting Influenza Mitigation Strategies

no code implementations16 Nov 2017 Pieter Libin, Timothy Verstraeten, Diederik M. Roijers, Jelena Grujic, Kristof Theys, Philippe Lemey, Ann Nowé

We evaluate these algorithms in a realistic experimental setting and demonstrate that it is possible to identify the optimal strategy using only a limited number of model evaluations, i. e., 2-to-3 times faster compared to the uniform sampling method, the predominant technique used for epidemiological decision making in the literature.

Decision Making Thompson Sampling

Analysing Congestion Problems in Multi-agent Reinforcement Learning

no code implementations28 Feb 2017 Roxana Rădulescu, Peter Vrancx, Ann Nowé

Congestion problems are omnipresent in today's complex networks and represent a challenge in many research domains.

Multi-agent Reinforcement Learning reinforcement-learning +1

Solving stable matching problems using answer set programming

no code implementations16 Dec 2015 Sofie De Clercq, Steven Schockaert, Martine De Cock, Ann Nowé

Since the introduction of the stable marriage problem (SMP) by Gale and Shapley (1962), several variants and extensions have been investigated.

Modeling Stable Matching Problems with Answer Set Programming

no code implementations28 Feb 2013 Sofie De Clercq, Steven Schockaert, Martine De Cock, Ann Nowé

Our encoding can easily be extended and adapted to the needs of specific applications.

Directed Policy Gradient for Safe Reinforcement Learning with Human Advice

no code implementations13 Aug 2018 Hélène Plisnier, Denis Steckelmacher, Tim Brys, Diederik M. Roijers, Ann Nowé

Our technique, Directed Policy Gradient (DPG), allows a teacher or backup policy to override the agent before it acts undesirably, while allowing the agent to leverage human advice or directives to learn faster.

reinforcement-learning Reinforcement Learning (RL) +1

The Actor-Advisor: Policy Gradient With Off-Policy Advice

no code implementations7 Feb 2019 Hélène Plisnier, Denis Steckelmacher, Diederik M. Roijers, Ann Nowé

In this paper, we propose an elegant solution, the Actor-Advisor architecture, in which a Policy Gradient actor learns from unbiased Monte-Carlo returns, while being shaped (or advised) by the Softmax policy arising from an off-policy critic.

Transfer Learning

Transfer Learning Across Simulated Robots With Different Sensors

no code implementations18 Jul 2019 Hélène Plisnier, Denis Steckelmacher, Diederik Roijers, Ann Nowé

After training in the lab, the robot should be able to get by without the expensive equipment that used to be available to it, and yet still be guaranteed to perform well on the field.

Transfer Learning

Multi-Objective Multi-Agent Decision Making: A Utility-based Analysis and Survey

no code implementations6 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.

Decision Making

IPC-Net: 3D point-cloud segmentation using deep inter-point convolutional layers

no code implementations30 Sep 2019 Felipe Gomez Marulanda, Pieter Libin, Timothy Verstraeten, Ann Nowé

In general, our approach outperforms PointNet on every family of 3D geometries on which the models were tested.

Point Cloud Segmentation

Fleet Control using Coregionalized Gaussian Process Policy Iteration

1 code implementation22 Nov 2019 Timothy Verstraeten, Pieter JK Libin, Ann Nowé

In many settings, as for example wind farms, multiple machines are instantiated to perform the same task, which is called a fleet.

Gaussian Processes reinforcement-learning +2

Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping

no code implementations15 Jan 2020 Eugenio Bargiacchi, Timothy Verstraeten, Diederik M. Roijers, Ann Nowé

We present a new model-based reinforcement learning algorithm, Cooperative Prioritized Sweeping, for efficient learning in multi-agent Markov decision processes.

Model-based Reinforcement Learning Multi-agent Reinforcement Learning +3

A utility-based analysis of equilibria in multi-objective normal form games

no code implementations17 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.

Model-predictive control and reinforcement learning in multi-energy system case studies

no code implementations20 Apr 2021 Glenn Ceusters, Román Cantú Rodríguez, Alberte Bouso García, Rüdiger Franke, Geert Deconinck, Lieve Helsen, Ann Nowé, Maarten Messagie, Luis Ramirez Camargo

Model-predictive-control (MPC) offers an optimal control technique to establish and ensure that the total operation cost of multi-energy systems remains at a minimum while fulfilling all system constraints.

Benchmarking Model Predictive Control +2

Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning

1 code implementation10 Jun 2021 Youri Coppens, Denis Steckelmacher, Catholijn M. Jonker, Ann Nowé

Then, to ensure that the rules explain a valid, non-degenerate policy, we introduce a refinement algorithm that fine-tunes the rules to obtain good performance when executed in the environment.

reinforcement-learning Reinforcement Learning (RL) +1

Dealing with Expert Bias in Collective Decision-Making

1 code implementation25 Jun 2021 Axel Abels, Tom Lenaerts, Vito Trianni, Ann Nowé

Quite some real-world problems can be formulated as decision-making problems wherein one must repeatedly make an appropriate choice from a set of alternatives.

Decision Making

Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning

no code implementations23 Dec 2021 Raphaël Avalos, Mathieu Reymond, Ann Nowé, Diederik M. Roijers

Many recent successful off-policy multi-agent reinforcement learning (MARL) algorithms for cooperative partially observable environments focus on finding factorized value functions, leading to convoluted network structures.

reinforcement-learning Reinforcement Learning (RL) +3

Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning

no code implementations11 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.

Decision Making Multi-Objective Reinforcement Learning +1

The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models

no code implementations6 Mar 2023 Raphael Avalos, Florent Delgrange, Ann Nowé, Guillermo A. Pérez, Diederik M. Roijers

Maintaining a probability distribution that models the belief over what the true state is can be used as a sufficient statistic of the history, but its computation requires access to the model of the environment and is often intractable.

An adaptive safety layer with hard constraints for safe reinforcement learning in multi-energy management systems

no code implementations18 Apr 2023 Glenn Ceusters, Muhammad Andy Putratama, Rüdiger Franke, Ann Nowé, Maarten Messagie

(II) introducing self-improving hard constraints, to increase the accuracy of the constraint functions as more and new data becomes available so that better policies can be learnt.

energy management Management +2

Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making

no code implementations2 May 2023 Axel Abels, Tom Lenaerts, Vito Trianni, Ann Nowé

Experts advising decision-makers are likely to display expertise which varies as a function of the problem instance.

Decision Making

Distributional Multi-Objective Decision Making

1 code implementation9 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.

Decision Making

Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning

no code implementations11 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

Synthesis of Hierarchical Controllers Based on Deep Reinforcement Learning Policies

no code implementations21 Feb 2024 Florent Delgrange, Guy Avni, Anna Lukina, Christian Schilling, Ann Nowé, Guillermo A. Pérez

We propose a novel approach to the problem of controller design for environments modeled as Markov decision processes (MDPs).

reinforcement-learning

Mitigating Biases in Collective Decision-Making: Enhancing Performance in the Face of Fake News

1 code implementation11 Mar 2024 Axel Abels, Elias Fernandez Domingos, Ann Nowé, Tom Lenaerts

Individual and social biases undermine the effectiveness of human advisers by inducing judgment errors which can disadvantage protected groups.

Decision Making

Cannot find the paper you are looking for? You can Submit a new open access paper.