Here are some of my recent research projects. For potential students: Please contact me if you are interested in doing a PhD, Master thesis, Bachelor thesis, or any other kind of project with me.
- Learning to communicate in MARL: This is an ongoing PhD project conducted by C. Zhu where I am the co-promoter and daily supervisor. See our recent survey paper on JAAMAS.
- (MA)RL with sparse reward and heterogeneous properties: This is an ongoing PhD project conducted by S. Han, where I am the co-promoter and daily supervisor. See our recent paper on ECAI.
- Use RL for natural language processing (NLP) tasks:
- Use deep RL for dialogue systems policy optimization: This is an ongoing collaborative research project with dr. Yangyang Zhao. See our recent papers on TASLP and TACL.
- Specialize NLP models through Reinforcement Learning: This is an ongoing PhD project conducted by Leon Eshuijs at VU, where I co-supervise (with Prof. Antske Fokkens). It is funded by the Hybrid Intelligence project. See our recent preprint paper (the full version has been accepted at CoNLL 2025 and will be online soon!).
- RL to augment the knowledge in conversational agents: This is an ongoing project conducted by Selene Baez Santamaria at VU & U. of Zurich.
- Use RL to support real-time human (healthcare) behaviors:
- This project 'Wie zorgt?' aims to develop an intelligent RL-based environment to decrease the pressure on the healthcare professional and improve the quality of care for the elderly with dementia. This is a collaborative project with HvA, Tue, and HAN and funded by SIA-Publiek. See our recent paper.
- This research is a collaborative work with TNO under the HI project. We aim to develop a knowledge-based dialogue system for clinical support of patients with Type 2 diabetes and optimize the interaction using RL. See our recent viewpoint paper.
- Understand public sentiment and communication from social media data during the COVID-19 outbreak period: This research started with NLP analysis in the PuReGoMe project and now we extend it to analyze the dynamics of communication networks (e.g. see our recent preprint paper on RL for information maximization). We have a great number of Dutch social media data and are open to collaborations.