This paper proposes an online transfer framework to capture the interaction among agents and shows that current transfer learning in reinforcement learning is a special case of online transfer. Furthermore, this paper re-characterizes existing agents-teaching-agents methods as online transfer and analyze one such teaching method in three ways. First, the convergence of Q-learning and Sarsa with tabular representation with a finite budget is proven. Second, the convergence of Q-learning and Sarsa with linear function approximation is established. Third, the we show the asymptotic performance cannot be hurt through teaching. Additionally, all theoretical results are empirically validated.

Exploring web and in particular social media data is an essential task to many of the subject matter experts in order to discover content around their subject of interest. It is important to provide them with a tool to define their scope of vocabulary, i.e what to search for, and suggest them commonly used terms besides the serendipitous terms allowing them to define their scope of explorations. This paper presents methods on constructing ``domain models" which are families of keywords and extractors to enable focus on social media documents relevant to a project using multiple channels of information extraction.

We describe an experiment in using IBM’s Watson cognitive system to teach about human-computer co-creativity in a Georgia Tech Spring 2015 class on computational creativity. The project-based class used Watson to support biologically inspired design, a design paradigm that uses biological systems as analogues for inventing technological systems. The twenty-four students in the class self-organized into six teams of four students each, and developed semester-long projects that built on Watson to support biologically inspired design. In this paper, we describe this experiment in using Watson to teach about human-computer co-creativity, present one project in detail, and summarize the remaining five projects. We also draw lessons on building on Watson for (i) supporting biologically inspired design, and (ii) enhancing human-computer co-creativity.

For young children, adults learning English, or individuals with language disorders, complex narratives are difficult to create and understand.  While narratives can easily be assessed in terms of their lexical and syntactic difficulty, automatically measuring the level of narrative complexity is a challenging problem.  We present and evaluate a preliminary system for assessing narrative complexity, which should help identify suitable texts for readers and assist in narrative skill evaluation.

We are interested in the development of an autonomous social robot whose goal is to promote collaborative behaviors in children while playing an interactive game.

We present a system that integrates robot task execution with user input and feedback at multiple abstraction levels in order to achieve greater adaptability in new environments. The user can specify a hierarchical task, with the system interactively proposing logical action groupings within the task. During execution, if tasks fail because objects specified in the initial task description are not found in the environment, the robot proposes substitutions autonomously in order to repair the plan and resume execution. The user can assist the robot by reviewing substitutions. Finally, the user can train the robot to recognize and manipulate novel objects, either during training or during execution. In addition to this single-user scenario, we propose extensions that leverage crowdsourced input to reduce the need for direct user feedback.

Intelligent systems rely on pattern recognition and signature-based approaches for a wide range of sensors enhancing situational awareness. For example, autonomous systems depend on environmental sensors to perform their tasks and secure systems depend on anomaly detection methods. The availability of large amount of data requires the processing of data in a “streaming” fashion with online algorithms. Yet, just as online learning can enhance adaptability to a non-stationary environment, it introduces vulnerabilities that can be manipulated by adversaries to achieve their goals while evading detection. Although human intelligence might have evolved from social interactions, machine intelligence has evolved as a human intelligence artifact and been kept isolated to avoid ethical dilemmas. As our adversaries become sophisticated, it might be time to revisit this question and examine how we can combine online learning and reasoning leading to the science of deceptive and counter-deceptive machines.

We present Fiascomatic , a mixed initiative system for generating consistent scenarios for the indie storytelling RPG Fiasco . Players can repeatedly generate scenarios, locking down aspects of a scenario they like and regenerating aspects they don’t, until they arrive at a scenario they find entertaining.  It is not a story generation system; it generates scenarios from which players then generate stories.  Nor is it intended to generate optimal scenarios; it generates random scenarios which the players can then curate according to their taste. Fiascomatic presents an interesting intermediate point between non-automated table-top RPGs and fully automated systems such as story generators or autonomous characters.  It is a tool that can be used by Fiasco players to speed the generation of game setups while preserving creative input on the part of the players, and by Fiasco playset authors to make automated playsets.

There has been a large body of research demonstrating that students that receive one-on-one tutoring perform, on average, significantly better than students learning via conventional classroom instruction when tested on the same material (Bloom 1984; VanLehn 2011). During tutoring, the teacher has the ability to tailor the instruction and support to the individual learner, creating a personalized learning environment for each student. Research involving robotic agents Figure 1: Child interacting with a NAO robot in a tutoring as tutors indicates that the physical presence of a robot tutor scenario can increase cognitive learning gains (Leyzberg et al. 2010). Further research shows that a robot tutor employing relatively simple personalization strategies can benefit the that on-demand help is useful in interactive learning environments learner (Leyzberg, Spaulding, and Scassellati 2014).

Recent progress in machine learning has lead to great advancements in robot intelligence and human-robot interaction (HRI). It is reported that robots can deeply understand visual scene information and describe the scenes in natural language using object recognition and natural language processing methods. Image-based question and answering (Q&A) systems can be used for enhancing HRI. However, despite these successful results, several key issues still remain to be discussed and improved. In particular, it is essential for an agent to act in a dynamic, uncertain, and asynchronous envi-ronment for achieving human-level robot intelligence. In this paper, we propose a prototype system for a video Q&A robot “Pororobot”. The system uses the state-of-the-art machine learning methods such as a deep concept hierarchy model. In our scenario, a robot and a child plays a video Q&A game together under real world environments. Here we demonstrate preliminary results of the proposed system and discuss some directions as future works.