Current projects and collaborations
Stable gradient learning in continuous games
Machine learning models with competing losses are notoriously challenging to train, e.g. zero-sum generative adversarial networks (GANs) or non-zero-sum reinforcement learning (RL) agents. We analyze and design learning algorithms used in these settings.
Human/machine sensorimotor games
In tasks involving adaptive algorithms and continuously-learning humans,
rich dynamic behaviors can prevent the system from reaching consensus.
Optimization interface for human autonomy
The aggressive dynamics of high-performance quadcopters demand agents to constantly be aware of the feedforward (planning) and feedback (reaction) policies of others.
Past projects
Snapshot of my projects before graduate school
Autonomous underwater vehicle (2016)
Underwater vehicle with acoustic receivers used to track leopard sharks.
Hybrid rocket motor (2015)
A rocket motor powered by acrylic and nitrous oxide.
Vibrational modes of a rocket in supersonic flight (2014)
Experiments with an amateur rocket to model its structural vibration.
Cistern mapping with ROVs (2013)
Remotely operated vehicles (ROVs) for scanning underwater cisterns.