TEAMSTER: Model-based reinforcement learning for ad hoc teamwork

This paper investigates the use of model-based reinforcement learning in the context of ad hoc teamwork. We introduce a novel approach, named TEAMSTER, where we propose learning both the environment's model and the model of the teammates' behavior separately. Compared to the state-of-the-art PLASTIC algorithms, our results in four different domains from the multi-agent systems literature show that TEAMSTER is more flexible than the PLASTIC-Model, by learning the environment's model instead of assuming a perfect hand-coded model, and more robust/efficient than PLASTIC-Policy, by being able to continuously adapt to newly encountered teams, without implicitly learning a new environment model from scratch.