I am an associate professor in the interactive intelligence group at TU Delft. My main research interests lie in the intersection between AI, ML and game theory. I will contribute to hybrid intelligence with expert knowledge about formal models of interaction over time. Specifically, I have expertise on multiagent extensions of MDPs and partially observable MDPs (POMDPs), and investigate game theoretic views of adversarial machine learning.

Roles in Hybrid Intelligence: Co-Coordinator SIG Reinforcement Learning, Supervisor, former co-coordinator of the Adaptive HI research line

Hybrid Intelligence Research Objectives: Adaptive HI

Hybrid Intelligence Projects:

• 16. Context Modeling for Dialog Systems, with dr. Christof Monz (UvA)
• 17. TUD (Meta-) learning to give feedback in interactive learning, with Herke van Hoof (UvA)
• 2.9 Bayesian multi-agent reinforcement learning for learning to collaborate with humans

Research interests: My main research interests lie in the intersection between AI, ML and game theory, in what I like to call interactive learning and decision making. This includes reinforcement learning, multiagent reinforcement learning, but also interactive machine learning settings such as generative adversarial networks.

Affiliations:

• TU Delft

More information: website