AAAI.2016 - Humans and AI

| Total: 4

#1 Personalized Alert Agent for Optimal User Performance [PDF] [Copy] [Kimi] [REL]

Authors: Avraham Shvartzon, Amos Azaria, Sarit Kraus, Claudia Goldman, Joachim Meyer, Omer Tsimhoni

Preventive maintenance is essential for the smooth operation of any equipment. Still, people occasionally do not maintain their equipment adequately. Maintenance alert systems attempt to remind people to perform maintenance. However, most of these systems do not provide alerts at the optimal timing, and nor do they take into account the time required for maintenance or compute the optimal timing for a specific user. We model the problem of maintenance performance, assuming maintenance is time consuming. We solve the optimal policy for the user, i.e., the optimal timing for a user to perform maintenance. This optimal strategy depends on the value of user's time, and thus it may vary from user to user and may change over time. %We present a game Based on the solved optimal strategy we present a personalized maintenance agent, which, depending on the value of user's time, provides alerts to the user when she should perform maintenance. In an experiment using a spaceship computer game, we show that receiving alerts from the personalized alert agent significantly improves user performance.


#2 Intelligent Advice Provisioning for Repeated Interaction [PDF] [Copy] [Kimi] [REL]

Authors: Priel Levy, David Sarne

This paper studies two suboptimal advice provisioning methods ("advisors") as an alternative to providing optimal advice in repeated advising settings. Providing users with suboptimal advice has been reported to be highly advantageous whenever the optimal advice is non-intuitive, hence might not be accepted by the user. Alas, prior methods that rely on suboptimal advice generation were designed primarily for a single-shot advice provisioning setting, hence their performance in repeated settings is questionable. Our methods, on the other hand, are tailored to the repeated interaction case. Comprehensive evaluation of the proposed methods, involving hundreds of human participants, reveals that both methods meet their primary design goal (either an increased user profit or an increased user satisfaction from the advisor), while performing at least as good with the alternative goal, compared to having people perform with: (a) no advisor at all; (b) an advisor providing the theoretic-optimal advice; and (c) an effective suboptimal-advice-based advisor designed for the non-repeated variant of our experimental framework.


#3 A Deep Choice Model [PDF] [Copy] [Kimi] [REL]

Authors: Makoto Otsuka, Takayuki Osogami

Human choice is complex in two ways. First, human choice often shows complex dependency on available alternatives. Second, human choice is often made after examining complex items such as images. The recently proposed choice model based on the restricted Boltzmann machine (RBM choice model) has been proved to represent three typical phenomena of human choice, which addresses the first complexity. We extend the RBM choice model to a deep choice model (DCM) to deal with the features of items, which are ignored in the RBM choice model. We then use deep learning to extract latent features from images and plug those latent features as input to the DCM. Our experiments show that the DCM adequately learns the choice that involves both of the two complexities in human choice.


#4 An Oral Exam for Measuring a Dialog System’s Capabilities [PDF] [Copy] [Kimi] [REL]

Authors: David Cohen, Ian Lane

This paper suggests a model and methodology for measuring the breadth and flexibility of a dialog system's capabilities. The approach relies on having human evaluators administer a targeted oral exam to a system and provide their subjective views of that system's performance on each test problem. We present results from one instantiation of this test being performed on two publicly-accessible dialog systems and a human, and show that the suggested metrics do provide useful insights into the relative strengths and weaknesses of these systems. Results suggest that this approach can be performed with reasonable reliability and with reasonable amounts of effort. We hope that authors will augment their reporting with this approach to improve clarity and make more direct progress toward broadly-capable dialog systems.