Projects
-
Deep reinforcement learning project.
End-of-quarter project for Stanford CS 224R, Deep Reinforcement Learning. Paired with Brion Ye. Topic in selection. Likely directions sit at the intersection of sample-efficient RL and the multi-agent driving stack we use elsewhere.
-
Experimental robotics project.
End-of-quarter project for Stanford CS 225A, Experimental Robotics. Topic in selection. Interest centers on closed-loop control of contact-rich manipulation, with a possible adaptive-sensing thread connecting back to the Arbabian Lab work.
-
Infrastructure-at-scale project.
End-of-quarter project for Stanford CS 153, Infrastructure at Scale. Topic in selection.