Thomas M. Moerland

Papers

Total Citations

H-Index

About

Thomas M. Moerland is a researcher at the intersection of reinforcement learning (RL) and artificial intelligence, with a focus on advancing both algorithmic foundations and biologically inspired models. His key research areas include model-based RL, continuous action spaces, and the integration of emotional mechanisms into learning agents. Moerland made a significant contribution with his work "A0C: Alpha Zero in Continuous Action Space" (2018, 20 citations), which extended the groundbreaking Alpha Zero algorithm—originally designed for discrete games like Chess and Go—to handle continuous action domains, a critical step for real-world RL applications such as robotics and control. In parallel, his paper "Fear and hope emerge from anticipation in model-based reinforcement learning" (2016, 16 citations) pioneered the study of emotion generation in sequential decision-making, connecting model-based RL with affective computing. This work explores how agents can develop anticipatory emotions like fear and hope, offering a novel pathway for designing more socially capable robots. Moerland’s research is notable for bridging technical RL advances with cognitive and emotional modeling, making his work relevant to both AI practitioners and researchers interested in human-like machine learning.