I am an undergraduate student majoring in Math-CS at Brown University, where I was fortunately advised by Professor Amy Greenwald and Chen Sun. My interest lies in the intersection of games, learning, and multi-agent interactions.
Selected Projects:
TOLD-ZERO - TDMPC-2 is a model-based reinforcement learning algorithm on continuous action control. In this work we present TOLD-ZERO, a generalization of the original paper that specializes in discrete action tasks and uses Monte-Carlo Tree Search as a local trajectory optimization method. We try to argue the role of planning in model-based RL in both continuous and discrete action tasks, specifically by bench-marking algorithms with or without planning on the LightZero Environment. The complete report could be found inside the TOLD-ZERO repo.
Pipelining Natural Language to Multi-Robot Task Allocation - This initiative aims to simplify commanding a team of robots through a logical intermediary. By translating natural language commands into linear temporal logic, we've enhanced the success rate of task execution. The approach supports complex commands and collaborative tasks between humans and teams of robots. The project write-up is accessible here.