Abstract In recent years, several methods have been proposed for implementing interactive similarity queries on multimedia databases. Common to all these methods is the idea to exploit user feedback in order to progressively adjust the query parameters and to eventually converge to an “optimal” parameter setting. However, all these methods also share the feature to “forget” user preferences acr...

A long term goal of Interactive Reinforcement Learning is to incorporate nonexpert human feedback to solve complex tasks. Some state-of-the-art methods have approached this problem by mapping human information to rewards and values and iterating over them to compute better control policies. In this paper we argue for an alternate, more effective characterization of human feedback: Policy Shapin...

Structured prediction from bandit feedback describes a learning scenario where instead of having access to a gold standard structure, a learner only receives partial feedback in form of the loss value of a predicted structure. We present new learning objectives and algorithms for this interactive scenario, focusing on convergence speed and ease of elicitability of feedback. We present supervise...

Dialogue management is the component of a dialogue system that determines the optimal action for the system to take at each turn. An important consideration for dialogue managers is the ability to adapt to new user behaviors unseen during training. In this paper, we investigate policy gradient based methods for interactive reinforcement learning where the agent receives action-specific feedback...

This study analyzed anonymous peer feedback among two groups of university students—a lower-performing class and a higher-performing class. Students used an audience response system to anonymously comment on each other’s work. Each or was categorized into one seven types: Praise+, Praise−, Criticism+, Criticism−, Combined Praise Criticism, Opinion, Irrelevant. The plus (+) minus (−) signs were ...

In this paper we present the XIMPEL interactive video platform. XIMPEL has been developed for the Clima Futura climate game, in which we use interactive video as a basis for scenario-driven games, with additional mini-games for elaborating on specific topics or tasks that arise during game play. XIMPEL has also been deployed in education, for creating short viral videos which allow for further ...

This paper contributes a first study into how different human users deliver simultaneous control and feedback signals during human-robot interaction. As part of this work, we formalize and present a general interactive learning framework for online cooperation between humans and reinforcement learning agents. In many humanmachine interaction settings, there is a growing gap between the degrees-...

In this paper, we address the topic of user-centered design (UCD) for cartography, GIScience, and visual analytics. Interactive maps are ubiquitous in modern society, yet they often fail to “work” as they could or should. UCD describes the process of ensuring interface success—map-based or otherwise—by gathering input and feedback from target users throughout the design and development of the i...