Controllers for robotic systems can be complex and difficult to write by hand. Learning offers an approach to improve a controller through direct feedback. Learning is not trivial, as the feedback does not tell the agent how to improve, only how well its current actions solve the given task. Learning...
We present a user study to investigate the impact of explanations on non-experts' understanding of reinforcement learning (RL) agents. We investigate both a common RL visualization, saliency maps (the focus of attention), and a more recent explanation type, reward-decomposition bars (predictions of future types of rewards). We designed a 124...
Autonomous multiagent teams can be used in complex exploration tasks to both expedite the exploration and improve the efficiency. However, use of multiagent systems presents additional challenges. Specifically, in domains where the agents' actions are tightly coupled, coordinating multiple agents to achieve cooperative behavior at the group level is difficult....
Cooperative multiagent systems are used as solution concepts in many application domains including air traffic control, satellite communications, and extra planetary exploration. As systems become more distributed and complex, we observe three phenomena. First, these systems cannot be accurately modeled, rendering traditional model based control methods inadequate. Second, system parameters...
Writing a program that performs well in a complex environment is a challenging task. In such problems, a method of deterministic programming combined with reinforcement learning (RL) can be helpful. However, current systems either force developers to encode knowledge in very specific forms (e.g., state-action features), or assume advanced RL...
Tensegrity structures are composed of pure compressional elements that are connected via a network of pure tensional elements. The concept of tensegrity promises numerous advantages to the field of robotics. Tensegrity robots are, however, notoriously difficult to control due to their oscillatory nature and nonlinear interaction between the components. Multiagent...
Auctions are used to solve resource allocation problem between many agents and many items in real-world settings. Unfortunately, in most cases, it is possible for selfish agents to manipulate the system for their own interest at the expense of the social welfare. Such manipulation can be prevented using the Vickrey-Clarke-Groves...
Air traffic flow management over the U.S. airpsace is a difficult problem. Current management approaches lead to hundreds of thousands of hours of delay, costing billions of dollars annually. Weather and airport conditions may instigate this delay, but routing decisions balancing delay with congestion contribute significantly to the propagation of...
Innovation is a key element for a product to achieve market success, but identifying it within product or even defining the term is a difficult task. Identifying innovation has been approached in many different ways. Experts in design engineering may identify innovative designs based on an analysis of a product's...
Partial programming is a field of study where users specify an outline or skeleton of a program, but leave various parts undefined. The undefined parts are then completed by an external mechanism to form a complete program. Adaptation-Based Programming (ABP) is a method of partial programming that utilizes techniques from...