Eugene Vinitsky MAD Games Workshop at ICRA 2024

MAD Games workshop on Multi-Agent Dynamic Games at ICRA 2024 was organized by Rahul Mangharam, Hongrui Zheng, Shuo Yang, Johannes Betz and Venkat Krovi. icra2024-madga...
Various types of KL-regularization towards human data have started to demonstrate the ability to empirically resolve challenges of equilibrium selection in many-player games. Unfortunately, very few domains have large datasets of human behavior that can be used to study the scalability and efficacy of this approach. We investigate these ideas in the driving context by trying to learn, via self-play, models of human driving. We demonstrate that this approach appears to yield highly capable agents that are human-like according to a variety of metrics.
Eugene Vinitsky is an assistant professor in Transportation Engineering at NYU, a member of the C2SMARTER consortium on congestion reduction, and a part-time research scientist at Apple. He works primarily on multi-agent learning with a focus on its potential use in transportation systems and robotics. At UC Berkeley, where he was advised by Alexandre Bayen, he received his PhD in controls engineering with a specialization in reinforcement learning and received an MS and BS in physics from UC Santa Barbara and Caltech respectively. During his PhD he spent time at DeepMind, Tesla Autopilot, and FAIR.