Peter Vamplew

A Practical Guide to Multi-Objective Reinforcement Learning and Planning

Real-world decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and...

Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI

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 and values. We...

Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment

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 conflicting values...

Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks

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 learning environments....

Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)

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 artificial. We...

Levels of explainable artificial intelligence for human-aligned conversational explanations

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 for this growth...

Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey

Broad Explainable Artificial Intelligence moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning...

Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety

The rapid advancement of artificial intelligence (AI) systems suggests that artificial general intelligence (AGI) systems may soon arrive. Many researchers are concerned that AIs and AGIs will...

Evaluating Human-like Explanations for Robot Actions in Reinforcement Learning Scenarios

Explainable artificial intelligence is a research field that tries to provide more transparency for autonomous intelligent systems. Explainability has been used, particularly in reinforcement...

Explainable robotic systems: Understanding goal-driven actions in a reinforcement learning scenario

Robotic 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...

Persistent Rule-based Interactive Reinforcement Learning

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-time. Current...

A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review

A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex...

A Multi-Objective Deep Reinforcement Learning Framework

This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We develop a high-performance MODRL framework that supports both...

A Demonstration of Issues with Value-Based Multiobjective Reinforcement Learning Under Stochastic State Transitions

We report a previously unidentified issue with model-free, value-based approaches to multiobjective reinforcement learning in the context of environments with stochastic state transitions. An...

Discrete-to-Deep Supervised Policy Learning

Neural networks are effective function approximators, but hard to train in the reinforcement learning (RL) context mainly because samples are correlated. For years, scholars have got around this...

A Survey of Multi-Objective Sequential Decision-Making

Sequential decision-making problems with multiple objectives arise naturally in practice and pose unique challenges for research in decision-theoretic planning and learning, which has largely...

The Combative Accretion Model - Multiobjective Optimisation Without Explicit Pareto Ranking

Learning the Value Systems of Societies with Preference-based Multi-objective Reinforcement Learning