Braxton Geary

Braxton is a Ph.D. student studying multi-agent reinforcement learning (MARL), with a focus on credit assignment and policy gradient methods for cooperative multi-agent systems. He is interested in understanding where the variance in multi-agent policy gradients comes from and in developing estimators that reduce it with provable guarantees, so that teams of agents can learn to coordinate more efficiently. Braxton previously received his Bachelor’s degree in Computer Science from Utah State University.