Research interests

I'm working on artificial intelligence for making games more fun to play, and on human-computer interaction techniques to make academic game AI more accessible for non-experts.

My current research focuses on creating aligned agent behaviors. One open challenge in this field is creating effective communication channels between the agent and the user. From the user agent, this channel has to enable it to explain its decision procedure to the user. From the user standpoint, communication has to provide her with the tools to give precise feedback to the agent. My collaborators at the Igarashi Lab, and I tackle this challenge by designing human-computer interaction methods that minimize the needed human feedback, and reinforcement learning based agents that explain their thinking process.

Publications