Simulating Team Tutoring in Multiagent Environments

A good team functions like a well-oiled machine. Team members train individually and together in order to do well as a team. Realistic simulations can offer safe and repeatable environments for teams to practice without real-world consequences. However, instructional support is often needed to help the team and individuals in case of mistakes and impasses and to guide the team on the path to success. In our work, we designed a simulated learning environment for teams of autonomous agents using PsychSim. The simulation provides a testbed for developing tutoring strategies suited for team training and for the skills it aims to engender. The simulation implements a “capture-the-flag” scenario, where a team of agents (the Blue team) must work to capture the flag being defended by an opposing team of agents (Red team). While the scenario is simple, the tutoring strategies to be used by a tutoring agent can be complex and dynamic. For example, what type of student behavior is considered a mistake and what should the tutoring agent instruct the student agents to do instead? In this paper, we will discuss the simulation experiments we designed to uncover tutoring strategies.

[1]  Michael C. Dorneich,et al.  The Development of a Testbed to Assess an Intelligent Tutoring System for Teams , 2015, AIED Workshops.

[2]  Stacy Marsella,et al.  PsychSim: Modeling Theory of Mind with Decision-Theoretic Agents , 2005, IJCAI.

[3]  David V. Pynadath,et al.  Socio-Cultural Modeling through Decision-Theoretic Agents with Theory of Mind , 2012 .

[4]  Stacy Marsella,et al.  Thespian: using multi-agent fitting to craft interactive drama , 2005, AAMAS '05.

[5]  Edmund H. Durfee,et al.  A Rigorous, Operational Formalization of Recursive Modeling , 1995, ICMAS.

[6]  Eliot Winer,et al.  Analysis of Team Tutoring Training Data , 2017 .

[7]  Stephen B Gilbert,et al.  Modality and Timing of Team Feedback: Implications for GIFT , 2014 .

[8]  David V. Pynadath,et al.  Modeling Theory of Mind and Cognitive Appraisal with Decision-Theoretic Agents , 2011 .

[9]  Eliot Winer,et al.  Evaluating Distributed Teams with the Team Multiple Errands Test , 2015 .

[10]  Sarit Kraus,et al.  Collaborative Plans for Complex Group Action , 1996, Artif. Intell..

[11]  Milind Tambe,et al.  The Communicative Multiagent Team Decision Problem: Analyzing Teamwork Theories and Models , 2011, J. Artif. Intell. Res..

[12]  David V. Pynadath,et al.  Building Trust in a Human-Robot Team with Automatically Generated Explanations , 2015 .

[13]  B. Mol,et al.  Multidisciplinary Team Training in a Simulation Setting for Acute Obstetric Emergencies: A Systematic Review , 2010, Obstetrics and gynecology.

[14]  Michael C. Dorneich,et al.  Taxonomy of Teams, Team Tasks, and Tutors , 2014 .

[15]  Ning Wang,et al.  Intelligent Agents for Virtual Simulation of Human-Robot Interaction , 2015, HCI.

[16]  Paula J. Durlach,et al.  BiLAT: A Game-Based Environment for Practicing Negotiation in a Cultural Context , 2009, Int. J. Artif. Intell. Educ..

[17]  Bart De Schutter,et al.  A Comprehensive Survey of Multiagent Reinforcement Learning , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[18]  Noboru Matsuda,et al.  Metacognitive Scaffolding Amplifies the Effect of Learning by Teaching a Teachable Agent , 2018, AIED.

[19]  Nicole C. Krämer,et al.  Negotiations in the Context of AIDS Prevention: An Agent-Based Model Using Theory of Mind , 2011, IVA.

[20]  Sean Luke,et al.  Cooperative Multi-Agent Learning: The State of the Art , 2005, Autonomous Agents and Multi-Agent Systems.

[21]  Milind Tambe,et al.  Intelligent Agents for Interactive Simulation Environments , 1995, AI Mag..

[22]  Benedict du Boulay.  Recent Meta-reviews and Meta–analyses of AIED Systems , 2015, International Journal of Artificial Intelligence in Education.

[23]  Phillip M. Harter,et al.  Simulation for Team Training and Assessment: Case Studies of Online Training with Virtual Worlds , 2008, World Journal of Surgery.

[24]  Craig Boutilier,et al.  Decision-Theoretic Planning: Structural Assumptions and Computational Leverage , 1999, J. Artif. Intell. Res..

[25]  Patrick Lardieri,et al.  The Advanced Embedded Training System (AETS): An Intelligent Embedded Tutoring System for Tactical Team Training , 1998 .

[26]  David V. Pynadath,et al.  PsychSim: Agent-based Modeling of Social Interactions and Influence , 2004, ICCM.

[27]  David V. Pynadath,et al.  Toward Acquiring a Human Behavior Model of Competition vs. Cooperation , 2015 .

[28]  Randall W. Hill,et al.  UrbanSim: Using Social Simulation to Train for Stability Operations , 2014 .

[29]  Manuela M. Veloso,et al.  Multiagent Systems: A Survey from a Machine Learning Perspective , 2000, Auton. Robots.

[30]  Lynn C. Miller,et al.  Socially Optimized Learning in Virtual Environments (SOLVE) , 2011, ICIDS.

[31]  Jeff Rickel,et al.  Virtual Humans for Team Training in Virtual Reality , 1999 .

[32]  Weixiong Zhang,et al.  Towards flexible teamwork in persistent teams , 1998, Proceedings International Conference on Multi Agent Systems (Cat. No.98EX160).

[33]  A. Gopnik,et al.  Natural theories of mind: Evolution, development and simulation of everyday mindreading , 2015 .

[34]  Michael C. Dorneich,et al.  Creating a Team Tutor Using GIFT , 2018, International Journal of Artificial Intelligence in Education.

[35]  Milind Tambe,et al.  Towards Flexible Teamwork , 1997, J. Artif. Intell. Res..

[36]  Robert A. Sottilare,et al.  Designing Adaptive Instruction for Teams: a Meta-Analysis , 2017, International Journal of Artificial Intelligence in Education.

[37]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..