Despite the popularity of multi-agent reinforcement learning (RL) in simulated and two-player applications, its success in messy real-world applications has been limited. A key challenge lies in its generalizability across problem variations, a common necessity for many real-world problems. Contextual reinforcement learning (CRL) formalizes learning policies that generalize across problem variations. However, the lack of standardized benchmarks for multi-agent CRL has hindered progress in the field. Such benchmarks are desired to be based on real-world applications to naturally capture the many open challenges of real-world problems that affect generalization. To bridge this gap, we propose IntersectionZoo, a comprehensive benchmark suite for multi-agent CRL through the real-world application of cooperative eco-driving in urban road networks. The task of cooperative eco-driving is to control a fleet of vehicles to reduce fleet-level vehicular emissions. By grounding IntersectionZoo in a real-world application, we naturally capture real-world problem characteristics, such as partial observability and multiple competing objectives. IntersectionZoo is built on data-informed simulations of 16,334 signalized intersections derived from 10 major US cities, modeled in an open-source industry-grade microscopic traffic simulator. By modeling factors affecting vehicular exhaust emissions (e.g., temperature, road conditions, travel demand), IntersectionZoo provides one million data-driven traffic scenarios. Using these traffic scenarios, we benchmark popular multi-agent RL and human-like driving algorithms and demonstrate that the popular multi-agent RL algorithms struggle to generalize in CRL settings.

With the rapid advances in vehicle-to-vehicle (V2V) communications, interest for leveraging V2V communications for different applications has also grown exponentially. Leader selection is an important task required in a number of V2V communications related applications. In this paper, a distributed leader selection algorithm is introduced for vehicular ad-hoc networks (VANET) over unreliable V2V communications. The algorithm is simple, lightweight, and tightly integrated with SAE 2735 protocol for vehicular networks. The goal of the algorithm is to provide a robust leader selection method for a group of vehicles to determine a temporary leader in a short time, which could benefit several newly proposed applications based on V2V in traffic control and autonomous driving related areas. Simulation results have verified the excellent convergence time, robustness, and other aspects of the algorithm.