Mehul Damani
Hello! I am a second year Ph.D. student at MIT, where I am advised by Jacob Andreas.
My high level research goal is to develop generally capable reinforcement learning (RL) systems that are aligned with human values and goals. I am particularly interested in methods that harness the common-sense knowledge of LLM’s to guide RL agents. I am also interested in studying cooperation in multi-agent systems, which encompasses both pure agent teams as well as human-AI teams. Finally, I am excited by the prospect of applying RL to solve real-world problems such as warehouse automation and traffic signal control.
Previously, I worked with Lerrel Pinto at NYU on developing automatic curriculum learning methods for RL agents. Before that, I was a part of the MARMot Lab at NUS, where I worked with Guillaume Sartoretti on applying multi-agent reinforcement learning to traffic signal control and multi-agent pathfinding.
Selected Publications
- NeurIPSMitigating Generative Agent Social DilemmasIn NeurIPS 2023 Foundation Models for Decision Making Workshop 2023
- TMLROpen Problems and Fundamental Limitations of Reinforcement Learning from Human FeedbackarXiv preprint arXiv:2307.15217 2023
- AAMASSocialLight: Distributed Cooperation Learning towards Network-Wide Traffic Signal ControlIn Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems 2023
- Springer