Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMay 2024
Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning
- Peter Vamplew,
- Cameron Foale,
- Conor F. Hayes,
- Patrick Mannion,
- Enda Howley,
- Richard Dazeley,
- Scott Johnson,
- Johan Källström,
- Gabriel Ramos,
- Roxana Radulescu,
- Willem Röpke,
- Diederik M. Roijers
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2717–2721Research 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 paper we extend ...
- ArticleApril 2024
TopFormer: Topology-Aware Transformer for Point Cloud Registration
AbstractThe extraction of robust feature descriptors is crucial for achieving accurate point cloud registration. While the attention mechanism plays an important role in enabling sparse point features to learn global position-aware contextual information, ...
- research-articleJune 2024
Elastic step DQN: A novel multi-step algorithm to alleviate overestimation in Deep Q-Networks
AbstractDeep Q-Networks algorithm (DQN) was the first reinforcement learning algorithm using deep neural network to successfully surpass human level performance in a number of Atari learning environments. However, divergent and unstable behaviour have ...
- research-articleNovember 2023
Segmentation-driven feature-preserving mesh denoising
The Visual Computer: International Journal of Computer Graphics (VISC), Volume 40, Issue 9Pages 6201–6217https://doi.org/10.1007/s00371-023-03161-wAbstractFeature-preserving mesh denoising has received noticeable attention in visual media, with the aim of recovering high-fidelity, clean mesh shapes from the ones that are contaminated by noise. Existing denoising methods often design smaller weights ...
- research-articleFebruary 2024
A Wearable Multi-Sensor Fusion Approach for Gender Recognition based on Deep Learning
ICBRA '23: Proceedings of the 2023 10th International Conference on Bioinformatics Research and ApplicationsPages 114–119https://doi.org/10.1145/3632047.3632065Human activity recognition (HAR) has gained significant attention over the last decade due to its usefulness in various fields, including healthcare, sports, rehabilitation, and wearable technology. HAR involves using sensors, such as wearables, to ...
-
- research-articleMay 2023
A Brief Guide to Multi-Objective Reinforcement Learning and Planning
- Conor F. Hayes,
- Roxana Rădulescu,
- Eugenio Bargiacchi,
- Johan Kallstrom,
- 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
AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent SystemsPages 1988–1990Real-world sequential decision-making tasks are usually complex, and require trade-offs between multiple, often conflicting, objectives. However, the majority of research in reinforcement learning (RL) and decision-theoretic planning assumes a single ...
- research-articleMay 2023
Scalar Reward is Not Enough
- Peter Vamplew,
- Benjamin J. Smith,
- Johan Källström,
- Gabriel Ramos,
- Roxana Rădulescu,
- Diederik M. Roijers,
- Conor F. Hayes,
- Friedrik Hentz,
- Patrick Mannion,
- Pieter J.K. Libin,
- Richard Dazeley,
- Cameron Foale
AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent SystemsPages 839–841Silver et al. (2021) posit that scalar reward maximisation is sufficient to underpin all intelligence and provides a suitable basis for artificial general intelligence (AGI). This extended abstract summarises the counter-argument from our JAAMAS paper.
- research-articleMay 2023
Overcoming weaknesses of density peak clustering using a data-dependent similarity measure
Highlights- Propose a new data-dependent similarity measure based on probability mass called MP-Similarity which is invariant to data representations (units/scales used ...
Density Peak Clustering (DPC) is a popular state-of-the-art clustering algorithm, which requires pairwise (dis)similarity of data objects to detect arbitrary shaped clusters. While it is shown to perform well for many applications, DPC ...
- research-articleApril 2023
AI apology: interactive multi-objective reinforcement learning for human-aligned AI
Neural Computing and Applications (NCAA), Volume 35, Issue 23Pages 16917–16930https://doi.org/10.1007/s00521-023-08586-xAbstractFor an Artificially Intelligent (AI) system to maintain alignment between human desires and its behaviour, it is important that the AI account for human preferences. This paper proposes and empirically evaluates the first approach to aligning ...
- research-articleMarch 2023
Explainable reinforcement learning for broad-XAI: a conceptual framework and survey
Neural Computing and Applications (NCAA), Volume 35, Issue 23Pages 16893–16916https://doi.org/10.1007/s00521-023-08423-1AbstractBroad-XAI moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning algorithms into a coherent explanation of an agent’s behaviour that is aligned to the ...
- research-articleOctober 2022
Scalar reward is not enough: a response to Silver, Singh, Precup and Sutton (2021)
- Peter Vamplew,
- Benjamin J. Smith,
- Johan Källström,
- Gabriel Ramos,
- Roxana Rădulescu,
- Diederik M. Roijers,
- Conor F. Hayes,
- Fredrik Heintz,
- Patrick Mannion,
- Pieter J. K. Libin,
- Richard Dazeley,
- Cameron Foale
Autonomous Agents and Multi-Agent Systems (KLU-AGNT), Volume 36, Issue 2https://doi.org/10.1007/s10458-022-09575-5AbstractThe 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 artificial, and provides a suitable basis for the creation of ...
- research-articleApril 2022
A practical guide to multi-objective reinforcement learning and planning
- 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
Autonomous Agents and Multi-Agent Systems (KLU-AGNT), Volume 36, Issue 1https://doi.org/10.1007/s10458-022-09552-yAbstractReal-world sequential decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and decision-theoretic planning either ...
- research-articleFebruary 2022
Discrete-to-deep reinforcement learning methods
Neural Computing and Applications (NCAA), Volume 34, Issue 3Pages 1713–1733https://doi.org/10.1007/s00521-021-06270-6AbstractNeural networks are effective function approximators, but hard to train in the reinforcement learning (RL) context mainly because samples are correlated. In complex problems, a neural RL approach is often able to learn a better solution than ...
- research-articleFebruary 2022
The impact of environmental stochasticity on value-based multiobjective reinforcement learning
Neural Computing and Applications (NCAA), Volume 34, Issue 3Pages 1783–1799https://doi.org/10.1007/s00521-021-05859-1AbstractA common approach to address multiobjective problems using reinforcement learning methods is to extend model-free, value-based algorithms such as Q-learning to use a vector of Q-values in combination with an appropriate action selection mechanism ...
- research-articleJanuary 2022
Human engagement providing evaluative and informative advice for interactive reinforcement learning
Neural Computing and Applications (NCAA), Volume 35, Issue 25Pages 18215–18230https://doi.org/10.1007/s00521-021-06850-6AbstractInteractive reinforcement learning proposes the use of externally sourced information in order to speed up the learning process. When interacting with a learner agent, humans may provide either evaluative or informative advice. Prior research has ...
- research-articleSeptember 2021
Persistent rule-based interactive reinforcement learning
Neural Computing and Applications (NCAA), Volume 35, Issue 32Pages 23411–23428https://doi.org/10.1007/s00521-021-06466-wAbstractInteractive reinforcement learning has allowed speeding up the learning process in autonomous agents by including a human trainer providing extra information to the agent in real-time. Current interactive reinforcement learning research has been ...
- research-articleAugust 2021
Explainable robotic systems: understanding goal-driven actions in a reinforcement learning scenario
Neural Computing and Applications (NCAA), Volume 35, Issue 25Pages 18113–18130https://doi.org/10.1007/s00521-021-06425-5AbstractRobotic systems are more present in our society everyday. In human–robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action understanding,...
- research-articleAugust 2021
A Prioritized objective actor-critic method for deep reinforcement learning
Neural Computing and Applications (NCAA), Volume 33, Issue 16Pages 10335–10349https://doi.org/10.1007/s00521-021-05795-0AbstractAn increasing number of complex problems have naturally posed significant challenges in decision-making theory and reinforcement learning practices. These problems often involve multiple conflicting reward signals that inherently cause agents’ ...
- posterNovember 2020
A Robust Approach for Continuous Interactive Reinforcement Learning
HAI '20: Proceedings of the 8th International Conference on Human-Agent InteractionPages 278–280https://doi.org/10.1145/3406499.3418769Interactive reinforcement learning is an approach in which an external trainer helps an agent to learn through advice. A trainer is useful in large or continuous scenarios; however, when the characteristics of the environment change over time, it can ...