PhD student at Beijing University of Posts and Telecommunications & Zhongguancun Academy.
I work on reinforcement learning, multi-agent reinforcement learning, and game AI, with a focus on robust evaluation, out-of-distribution opponent generalization, and agent behavior in complex games.
- Robust evaluation for reinforcement learning agents
- Generalization to held-out and out-of-distribution opponents
- Long-context decision making for LLM agents in real games
- Personal homepage: me.alltroll.net
- Google Scholar: profile
- Email: alltroll@outlook.com, zikangli@bupt.edu.cn