Collaborate and Explain on the Fly: Nonmonotonic Logical Reasoning and Incremental Learning for Ad Hoc Teamwork

This paper describes an architecture for ad hoc teamwork, i.e., to enable an agent to collaborate with other agents “on the fly". State of the art frameworks for ad hoc teamwork often pursue a data-driven approach, using a large labeled dataset of prior observations to model the behavior of other agents and to determine the ad hoc agent’s behavior. These models are computationally expensive to learn, lack transparency, and make it difficult to recognize and adapt to previously unseen changes. In a departure from existing work, we introduce an architecture for ad hoc teamwork that performs non-monotonic logical reasoning with prior commonsense domain knowledge and models that are learned and revised rapidly from limited examples to predict the behavior of other agents. In addition, the architecture enables the agent to provide relational descriptions as on-demand explanations of its decisions and beliefs in response to different types of questions. We evaluate the architecture’s capabilities in two benchmark multiagent collaboration domains: Fort Attack and Half field Offense, in comparison with data-driven and knowledge-driven baselines.