I am Shihan Wang and I work as an assistant professor in the Intelligent Systems group at Utrecht University. My research interests lie in developing efficient, scalable and reliable reinforcement learning (RL) approaches to solve real-world problems. I am particularly interested in how RL algorithms can learn optimal policies through efficient and reliable human-agent or agent-agent interactions (communication). My research has also been applied to dialogue, healthcare and autonomous driving domains.

Roles in Hybrid Intelligence: Participant, Supervisor

Hybrid Intelligence Research Objectives: Adaptive HI

Hybrid Intelligence Projects:

• 2.3 VU Specializing NLP models through reinforcement learning

Research interests: Reinforcement Learning: learning through efficient and reliable interactions (communication), covers both single-agent and multi-agent RL settings.

Affiliations:

• Intelligent Systems, Utrecht University

More information: website Utrecht University