About me
I am a final-year Ph.D. student in the Machine Learning group at the University of Kaiserslautern-Landau, supervised by Professor Sophie Fellenz. My research primarily focuses on language-based reinforcement learning and value-aligned decision-making.
🐣 Research Interests
- Language-Based Reinforcement Learning: Many stable RL algorithms have not yet been directly utilized in language-based RL agents. This prompts a crucial research question: Can well-established RL algorithms be successfully adapted to operate in language-centric contexts?
- Ethical Reinforcement Learning: With the increasing capabilities of RL agents, ensuring the morally responsible behavior of an agent is a growing concern. Our goal is to align human or LLM-labeled moral scores with the RL agent.
- Human Preference Alignment in RL: Balancing safety, efficiency, and performance using diffusion-based planning, integrating human preference at infernece time without retraining.
🐥 Publications
- W.Li, et al. (2026) TORA: Train Once, Realign Anytime for Offline Multi-Objective Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, (to appear).
- W. Li, et al. (2025). Inference-Time Value Alignment in Offline Reinforcement Learning: Leveraging LLMs for Reward and Ethical Guidance. Workshop on WORDPLAY: WHEN LANGUAGE MEETS GAMES at EMNLP. Poster
- W. Li, W. Mustafa, et al. (2025). Inference-Time Preference-Aligned Diffusion Planning for Safe Offline Reinforcement Learning. Proceedings of the Third Workshop on Hybrid Human-Machine Learning and Decision Making (HHMLDM) at ECML-PKDD (Oral Presentation).
- W. Li, R. Devidze, W. Mustafa, and S. Fellenz.(2024) Ethics in Action: Training Reinforcement Learning Agent for Moral Decision-making In Text-based Adventure Games. Proceedings of International Conference on Artificial Intelligence and Statistics (AISTATS)
- W. Li, R. Devidze, S. Fellenz.(2023) Learning to play text-based adventure games with maximum entropy reinforcement learning. European Conference on Machine Learning and Data Mining (ECML-PKDD) Abstract Poster code
- W. Li.et.al.(2022),Topic-Guided Knowledge Graph Construction for Argument Mining. IEEE International Conference on Big Knowledge(ICBK)
📝 Teaching
I supervise Master projects and Thesis. Please contact me if you are interested in the following topics:
- Deep Reinforcement learning with application to chemical data.
- Pre-training LLMs for molecular generation