Hello! I am currently doing my PhD studies at the Division of Robotics, Perception and Learning (RPL) at KTH Royal Institute of Technology in Stockholm, Sweden. My research explores how to elicit and incorporate human feedback in the development of autonomous agents, with a focus on the design of believable NPCs in video games. We want to develop novel algorithms that align human feedback with models by extending existing active and preference learning methods. We also explore novel human-machine interaction modalities for feedback.

Projects

Open-Source Benchmark for Automated Testing and Validation of Complex 3D Game Environments (OSB3D)

William Ahlberg, Julia Hannu, Daniel de Leng, Fredrik Heintz, Alessandro Sestini, Linus Gisslén

Paper Code

Publications

A Call for Deeper Collaboration Between Robotics and Game Development

IEEE Conference on Games (CoG) 2025

Iolanda Leite, William Ahlberg, André Pereira, Alessandro Sestini, Linus Gisslén, Konrad Tollmar

Paper

Exploring Model-based Shielding for Non-Player Character Behaviour

Reinforcement Learning and Video Games Workshop at RLC 2025

William Ahlberg, Konrad Tollmar, Alessandro Sestini, Linus Gisslén, Iolanda Leite

Paper

Generating Personas for Games with Multimodal Adversarial Imitation Learning

IEEE Conference on Games (CoG) 2023

William Ahlberg, Alessandro Sestini, Konrad Tollmar, Linus Gisslén

Paper