3 papers
cs.CY2024
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…
cs.LG2024
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…
cs.LG2024
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…