447 citations · 697 across the 26 of their papers we have counts for
29 papers
It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learning
Liam P. H. Mertens, Lucas N. Alegre, Florent Delgrange +3
Time is of the essence when dealing with multiple reward signals and non-linear utility. In this paper we argue that the current main approaches in multi-objective RL (SER and ESR)…
OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning
Emil Mittag, Richard Dazeley, Peter Vamplew
Reliable reinforcement learning (RL) agents must maintain operational integrity amidst sensor malfunctions, dynamic disturbances, and slow environmental shifts. The detection of ou…
Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning
Adrian Ly, Richard Dazeley, Peter Vamplew +2
Deep Q-networks use target networks to stabilise bootstrapped value learning, but the standard hard copy update also introduces a tradeoff. Holding the target network fixed, improv…
Multi-objective Reinforcement Learning With Augmented States Requires Rewards After Deployment
Peter Vamplew, Cameron Foale
This research note identifies a previously overlooked distinction between multi-objective reinforcement learning (MORL), and more conventional single-objective reinforcement learni…
Learning the Value Systems of Societies with Preference-based Multi-objective Reinforcement Learning
Andrés Holgado-Sánchez, Peter Vamplew, Richard Dazeley +2
Value-aware AI should recognise human values and adapt to the value systems (value-based preferences) of different users. This requires operationalization of values, which can be p…
ES-C51: Expected Sarsa Based C51 Distributional Reinforcement Learning Algorithm
Rijul Tandon, Peter Vamplew, Cameron Foale
In most value-based reinforcement learning (RL) algorithms, the agent estimates only the expected reward for each action and selects the action with the highest reward. In contrast…
Ensemble Elastic DQN: A Step Dependent Ensemble Approach for Reducing Overestimation in Deep Value-Based Reinforcement Learning
Adrian Ly, Richard Dazeley, Peter Vamplew +2
Deep Q-Networks (DQN) can suffer from overestimation bias because bootstrapped targets use a maximisation operation over noisy value estimates. Ensemble-based methods and multi-ste…
On Generalization Across Environments In Multi-Objective Reinforcement Learning
Jayden Teoh, Pradeep Varakantham, Peter Vamplew
Real-world sequential decision-making tasks often require balancing trade-offs between multiple conflicting objectives, making Multi-Objective Reinforcement Learning (MORL) an incr…
AI Apology: A Critical Review of Apology in AI Systems
Hadassah Harland, Richard Dazeley, Hashini Senaratne +3
Apologies are a powerful tool used in human-human interactions to provide affective support, regulate social processes, and exchange information following a trust violation. The em…
Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI
Hadassah Harland, Richard Dazeley, Peter Vamplew +3
Emerging research in Pluralistic Artificial Intelligence (AI) alignment seeks to address how intelligent systems can be designed and deployed in accordance with diverse human needs…
Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment
Peter Vamplew, Conor F Hayes, Cameron Foale +2
Reinforcement learning (RL) is a valuable tool for the creation of AI systems. However it may be problematic to adequately align RL based on scalar rewards if there are multiple co…
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…
Issues with Value-Based Multi-objective Reinforcement Learning: Value Function Interference and Overestimation Sensitivity
Peter Vamplew, Ethan, Watkins +2
Multi-objective reinforcement learning (MORL) algorithms extend conventional reinforcement learning (RL) to the more general case of problems with multiple, conflicting objectives,…
An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments
Kewen Ding, Peter Vamplew, Cameron Foale +1
One common approach to solve multi-objective reinforcement learning (MORL) problems is to extend conventional Q-learning by using vector Q-values in combination with a utility func…
Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety
Catalin Mitelut, Ben Smith, Peter Vamplew
The rapid advancement of artificial intelligence (AI) systems suggests that artificial general intelligence (AGI) systems may soon arrive. Many researchers are concerned that AIs a…
Broad-persistent Advice for Interactive Reinforcement Learning Scenarios
Francisco Cruz, Adam Bignold, Hung Son Nguyen +2
The use of interactive advice in reinforcement learning scenarios allows for speeding up the learning process for autonomous agents. Current interactive reinforcement learning rese…
Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks
Adrian Ly, Richard Dazeley, Peter Vamplew +2
Deep 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 learni…
Evaluating Human-like Explanations for Robot Actions in Reinforcement Learning Scenarios
Francisco Cruz, Charlotte Young, Richard Dazeley +1
Explainable artificial intelligence is a research field that tries to provide more transparency for autonomous intelligent systems. Explainability has been used, particularly in re…
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…
Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey
Richard Dazeley, Peter Vamplew, Francisco Cruz
Broad Explainable Artificial Intelligence moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machin…
Levels of explainable artificial intelligence for human-aligned conversational explanations
Richard Dazeley, Peter Vamplew, Cameron Foale +3
Over the last few years there has been rapid research growth into eXplainable Artificial Intelligence (XAI) and the closely aligned Interpretable Machine Learning (IML). Drivers fo…
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…
Persistent Rule-based Interactive Reinforcement Learning
Adam Bignold, Francisco Cruz, Richard Dazeley +2
Interactive 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-t…
Human Engagement Providing Evaluative and Informative Advice for Interactive Reinforcement Learning
Adam Bignold, Francisco Cruz, Richard Dazeley +2
Interactive 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 p…