Stochastic control and reinforcement learning have seen rapid growth in recent years, driven by advances in dynamic programming, approximate inference, deep learning, and high-performance computing. These developments have enabled increasingly effective approaches to sequential decision-making under uncertainty, with impactful applications in robotics and autonomous systems, networking and resource allocation, finance, and healthcare. Despite this progress, several core challenges remain open. These include designing algorithms that are robust to noise, distribution shift, and adversarial effects; improving sample efficiency and computational scalability; establishing stronger theoretical guarantees for modern methods; and translating theoretical insights into reliable, deployable systems.
To help address these challenges and catalyze cross-disciplinary collaboration, this workshop, held in conjunction with ACM SIGMETRICS 2026, will bring together researchers and practitioners from stochastic control, reinforcement learning, optimization, operations research, and adjacent areas. The program will feature invited talks by leading speakers and structured opportunities for discussion and community engagement. In particular, we will host panel discussions at the end of each half-day session to facilitate exchange of perspectives on recent breakthroughs, open problems, and promising directions for future research, and to encourage interaction between the speakers and the audience.
Organizers: Gauri Joshi (Carnegie Mellon University), Mehrdad Moharrami (University of Iowa), Srinivas Shakkottai (University of Texas A&M),Â
Date: Friday, June 12th
Location: Ann Arbor, Michigan