This work is largely funded by the National Science Foundation (CNS-1634136, CNS-1646912, CNS-1656873, CNS-1736582, CNS-1836819).

Certifiable Reinforcement Learning

joint with Sam Burden (UW); Sam Coogan (GaTech)
Goal: develop algorithms for reinforcement learning with certificates of performance with assessment on benchmark problems. Applications include intelligent infrastructure (societal-scale CPS) and human-in-the-loop systems.

Adaptive Mechanism Design

Goal: in situations of asymmetric information, design incentive or information shaping schemes for changing user behavior via algorithmic mechanisms, with provable guarantees on performance, that leverage behavioral models capturing salient features of the human decision-making process.
Between Two Firms 

Performance Guarantees for Multi-Agent Learning

Goal: derive performance guarantees for classes of (competitive and cooperative) multi-agent learning algorithms in non-stationary environments. Such tools are useful for both analysis of the behavior of coupled learning agents as well as synthesizing mechanisms for shaping agent behavior.


Urban Mobility
Between Two Firms 

Human-Machine Interaction
Between Two Firms 

Online Platforms
Between Two Firms