W M W Michael

Papers

Total Citations

H-Index

About

W. M. W. Michael is a researcher in artificial intelligence and machine learning, with a particular focus on agent-based systems and behaviour acquisition. His most cited work, "Learning state-based behaviour using temporally related cases" (2011, 11 citations), addresses a key challenge in AI: enabling software agents to learn complex behaviours through observation rather than explicit programming. Michael’s approach leverages temporally related cases, allowing agents to infer an expert’s decision-making processes by examining sequences of actions and inputs over time. This work contributes to the broader field of learning by observation, offering a more flexible and intuitive method for training autonomous systems. While his citation count is modest, his research has implications for robotics, intelligent tutoring systems, and human-computer interaction, where agents must adapt to dynamic environments without manual coding. Michael’s contributions highlight the potential of case-based reasoning and temporal analysis in creating more adaptive, human-like AI, making his work a valuable reference for students and researchers exploring behaviour learning in autonomous agents.