Announced strategy types in multiagent RL for conflict-avoidance in the national airspace

Automated conflict-avoidance for unmanned aerial systems is quickly becoming feasible due to near-future advances in communication guarantees. The NextGen Implementation Plan introduced by the FAA lays out requirements for air traffic in the US airspace to be implemented by 2020. This includes mandates for the introduction of the automatic de-pendent surveillance broadcast (ADS-B) on each system in the airspace, which is a plane-installed system that broad-casts information about a plane in the airspace. Optionally, a pilot can choose to install the traffic information service broadcast (TIS-B) system, which allows a plane to observe ADS-B information for a 15-mile radius. This enhanced communication lends itself well to the for-mation of a multiagent system to model conflict-resolution in the air. But with a variety of different potential reactions by pilots in a conflict situation, a robust response structure must be developed. In this work, we introduce agents to make distributed decisions regarding rerouting for conflict-avoidance, and explore the possible benefit of stereotyping in this domain. We demonstrate also that the availability of avoidance type information can improve performance by reducing agent noise in a simple system reward formulation