Learning from Demonstration to be a Good Team Member in a Role Playing Game

We present an approach that uses learning from demonstration in a computer role playing game. We describe a behavior engine that uses case-based reasoning. The behavior engine accepts observation traces of human playing decisions and produces a sequence of actions which can then be carried out by an artificial agent within the gaming environment. Our work focuses on team-based role playing games, where the agents produced by the behavior engine act as team members within a mixed human-agent team. We present the results of a study we conducted, where we assess both the quantitative and qualitative performance difference between human-only teams compared with hybrid human-agent teams.

Learning from Demonstration to be a Good Team Member in a Role Playing Game

by Michael Silva, Silas McCroskey, Jonathan Rubin, Michael Youngblood, Ashwin Ram

26th International FLAIRS Conference on Artificial Intelligence (FLAIRS-13).
www.cc.gatech.edu/faculty/ashwin/papers/er-13-01.pdf

The Patient Portal Conundrum

Recent “Meaningful Use” legislation requires healthcare providers to (Stage 1) capture patient information in electronic health records, (Stage 2) create portals to enable online access for patients and providers, and (Stage 3) demonstrate improved quality of care. All of which sounds like a great idea…but will it work?
 
At PARC we believe in anthropologist Margaret Mead‘s driving principle: “What people say, what people do, and what people say they do are entirely different things.” We know consumers access healthcare information online, but what do they actually do when they’re there?
 
NPR Marketplace cites a report by healthcare research firm National Research indicating 96% of the nearly 23,000 consumers it surveyed recently use Facebook to gather information about health care, with 28% using YouTube and 22% using Twitter. In fact, social media has been called “the biggest threat to healthcare portals like WebMD”.
 
If consumers don’t use healthcare portals, how will we get “meaningful use” by creating them? I will attempt to answer this question (hint: think Augmented Social Cognition) but I fully expect to raise a lot more questions in the process. Come ready to ask and argue, and maybe we will find answers together.
 
Invited talk at Breakaway Healthcare Forum, held in conjunction with TEDMED, April 16, 2013. 
 

SLIDES:

Health != Healthcare: New Technologies for Consumer Health & Wellness

In a recent Wall Street Journal essay, Marc Andreessen wrote: “Software is eating the world. Over the next 10 years, I expect many more industries to be disrupted by software. Healthcare and education are next up for fundamental software-based transformation.”

What is the impending disruption in healthcare, and what is PARC doing in this space? I’ll provide an overview of PARC’s healthcare program, including market need, business opportunity, and research thrusts.

A key insight is that health and healthcare are two different markets. I’ll explain what this means and why this creates breakthrough opportunities for Augmented Social Cognition—in particular, through the confluence of three technologies: social, mobile, and gamification. Under the hood, artificial Intelligence (AI) techniques are used to augment human cognition and interaction, creating a new generation of “intelligent social web” technologies.

These technologies combine the benefits of the “information web” with those of the “social web”, enabling new consumer-centric approaches to health and wellness that increase engagement, improve health literacy and promote behavior change. I’ll give several examples of new technologies in the market and highlight research challenges that still need to be addressed.

I’m looking to engage, not to lecture, so come prepared to discuss, argue, and share ideas!

Keynote talk at WWW-2012 Web Intelligence & Communities workshop, Lyon, France, April 16, 2012.
Invited seminar at XRCE research center, Grenoble, France, April 18, 2012.

SLIDES

Socio-Semantic Conversational Information Access

We develop an innovative approach to delivering relevant information using a combination of socio-semantic search and filtering approaches. The goal is to facilitate timely and relevant information access through the medium of conversations by mixing past community specific conversational knowledge and web information access to recommend and connect users and information together. Conversational Information Access is a socio-semantic search and recommendation activity with the goal to interactively engage people in conversations by receiving agent supported recommendations. It is useful because people engage in online social discussions unlike solitary search; the agent brings in relevant information as well as identifies relevant users; participants provide feedback during the conversation that the agent uses to improve its recommendations.

Socio-Semantic Conversational Information Access

by Saurav Sahay, Ashwin Ram

WWW-2012 Workshop on Community Question Answering on the Web (CQA-12).

Health : Healthcare :: Learning : Education

With the advent of open education resources, social networking technologies and new pedagogies for online and blended learning, we are in the early stages of a significant disruption in current models of education. ‘Learning’ is beginning to peel away from ‘Education’ as a separate market, with its own set of opportunities and challenges for practitioners, technologists, and entrepreneurs. While ‘education’ is driven by schools, colleges, and governments, ‘learning’ focuses on empowering the individual to take charge of their learning.

Interestingly, a similar phenomenon is occurring in healthcare, fueled by the confluence of similar trends and technologies: open health resources, social networking technologies and new methodologies for consumer engagement. ‘Health’ is starting to emerge as a separate and disruptive market, with its own opportunities and challenges. While ‘healthcare’ is driven by providers, payers, and governments, ‘health’ focuses on empowering the consumer to take charge of their health and wellness. 

In this talk, I discuss recent trends in these two industries, explain why they are analogous, and discuss opportunities for user experience, big data, analytics and social capital research. I provide examples of social, mobile, and game technologies that are creating the disruption, and highlight key research challenges that are yet to be addressed.

Invited talk at UC Berkeley, iSchool “Thought Leaders in Data Science and Analytics”, April 11, 2012. 

SLIDES

Taking Advantage of Now: The Consumer Health & Wellness Scene

Taking Advantage of Now:
The Consumer Health & Wellness Scene

  • Lifestyle Innovation: defining successful business models
  • Opportunities on the horizon for corporates and investors
  • Innovation Partnering: strategic alliances at work to maximize consumer health & wellness appetite
  • Moving Goalposts: Market assessment to increase product pipelines

Moderator:

  • Will Rosenzweig, co-founder and Managing Director – Physic Ventures

Panelists:

  • Mark Murrison, President, Marketing and Innovation – MDVIP
  • Jack Young, Senior Investment Manager – Qualcomm Ventures
  • Mark Kapcynski, Corporate Development – Experian Consumer Direct
  • John Deedrick, Managing Director – Linn Grove Ventures
  • Ashwin Ram, Research Fellow & Area Manager of Socio-cognitive Computing, PARC a Xerox company
Invited panel presentation at IBF Consumer Health & Wellness Innovation Summit, Newport Beach, CA, February 9, 2012
ibfconferences.com/health-wellness-innovation-summit.html

Transforming the Industry: Watson in Education

Watson, named after IBM founder Thomas J. Watson, was built by a team of IBM scientists with valuable help from research partners from Carnegie Mellon University, University of Texas, University of Southern California, University of Massachusetts, University of Trento (Italy), MIT, RPI, and the University of Albany. The team set out to accomplish a grand challenge—to build a computing system that rivals a human’s ability to answer questions posed in natural language with speed, accuracy and confidence. Watson passed its first test on Jeopardy! in February 2011, but the real test will be in applying the underlying systems, data management and analytics technology across different industries, especially in education.

Invited panel presentation at IBM Watson in Education: Transforming the Industry, IBM Almaden Research Center, November 16, 2011