No abstract

The authors argue that design studies, like all scientific work, must comport with guiding scientific principles and provide adequate warrants for their knowledge claims. The issue is whether their knowledge claims can be warranted. By their very nature, design studies are complex, multivariate, multilevel, and interventionist, making warrants particularly difficult to establish. Moreover, many of these studies, intended or not, rely on narrative accounts to communicate and justify their findings. Although narratives often purport to be true, there is nothing in narrative form that guarantees veracity. The authors provide a framework that links design-study research questions as they evolve over time with corresponding research methods. In this way, an integration can be seen of research methods focused on discovery with methods focused on validation of claims.

No abstract

Simulation is an appealing option for validating the safety of autonomous vehicles. Generative Adversarial Imitation Learning (GAIL) has recently been shown to learn representative human driver models. These human driver models were learned through training in single-agent environments, but they have difficulty in generalizing to multi-agent driving scenarios. We argue these difficulties arise because observations at training and test time are sampled from different distributions. This difference makes such models unsuitable for the simulation of driving scenes, where multiple agents must interact realistically over long time horizons. We extend GAIL to address these shortcomings through a parameter-sharing approach grounded in curriculum learning. Compared with single-agent GAIL policies, policies generated by our PS-GAIL method prove superior at interacting stably in a multi-agent setting and capturing the emergent behavior of human drivers. * Indicates equal contribution.

The dialogue re-presented in this article is intended to foster mutual engagement—and opportunity for learning—across different perspectives on research within the education research community. Participants in the dialogue each addressed the following questions: (1) What are the touchstones by which you judge quality or rigor in education research (for a single study, a set of studies, or a “field” or community of researchers in dialogue)? What is your chief concern or fear that the touchstones guard against? (2) Where do you see challenges to your perspective in the perspectives of other members of the panel? How might your perspective evolve to respond to those challenges? Given all of this, what are the implications for the preparation of education researchers? Opening and closing comments set the dialogue in historical context, highlight issues raised, and suggest next steps for collaborative learning from the diversity of perspectives in our field.

No abstract

No abstract

Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-world datasets. Such behaviors arise due to the many local interactions between agents that are not commonly accounted for in imitation learning. This paper proposes Reward Augmented Imitation Learning (RAIL), which integrates reward augmentation into the multi-agent imitation learning framework and allows the designer to specify prior knowledge in a principled fashion. We prove that convergence guarantees for the imitation learning process are preserved under the application of reward augmentation. This method is validated in a driving scenario, where an entire traffic scene is controlled by driving policies learned using our proposed algorithm. Further, we demonstrate improved performance in comparison to traditional imitation learning algorithms both in terms of the local actions of a single agent and the behavior of emergent properties in complex, multi-agent settings.