Back to the future: towards a reasoning and learning architecture for ad hoc teamwork

Figure 1: Screenshot from the Fort Attack environment. Consider a team of three guards (in green) trying to defend a fort from a team of three attackers (in red) in Figure 1. In this “Fort Attack” (FA) domain, each agent can move in one of four cardinal directions with a particular velocity, rotate clockwise or […]

aaai2023 architecture articles clockwise environment future reasoning team teamwork