Interactive Task Learning

This article presents a new research area called interactive task learning (ITL), in which an agent actively tries to learn not just how to perform a task better but the actual definition of a task through natural interaction with a human instructor while attempting to perform the task. The authors provide an analysis of desiderata for ITL systems, a review of related work, and a discussion of possible application areas for ITL systems.

[1]  Gordon Cheng,et al.  Learning Similar Tasks From Observation and Practice , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Kenneth D. Forbus,et al.  Learning Qualitative Models by Demonstration , 2012, AAAI.

[3]  VelosoManuela,et al.  A survey of robot learning from demonstration , 2009 .

[4]  Gordon Cheng,et al.  Learning tasks from observation and practice , 2004, Robotics Auton. Syst..

[5]  Claude Sammut,et al.  Learning to Fly , 1992, ML.

[6]  Patrick Suppes,et al.  Language and Learning for Robots , 1994 .

[7]  M. David Merrill,et al.  First principles of instruction , 2012 .

[8]  Dario D. Salvucci.  Integration and Reuse in Cognitive Skill Acquisition , 2013, Cogn. Sci..

[9]  Kenneth D. Forbus,et al.  Domain transfer via cross-domain analogy , 2009, Cognitive Systems Research.

[10]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[11]  Nathanael Chambers,et al.  PLOW: A Collaborative Task Learning Agent , 2007, AAAI.

[12]  Kenneth D. Forbus,et al.  Multimodal knowledge capture from text and diagrams , 2009, K-CAP '09.

[13]  Rajiv T. Maheswaran,et al.  Learning and Evaluating Human-Like NPC Behaviors in Dynamic Games , 2011, AIIDE.

[14]  Herbert A. Simon,et al.  THE MIND'S EYE IN CHESS , 1988 .

[15]  Pat Langley,et al.  Cognitive architectures: Research issues and challenges , 2009, Cognitive Systems Research.

[16]  Frank J. Lee,et al.  Production Compilation: A Simple Mechanism to Model Complex Skill Acquisition , 2003, Hum. Factors.

[17]  John E. Laird,et al.  Interactive Task Learning for Simple Games , 2014 .

[18]  Lukasz Kaiser,et al.  Learning Games from Videos Guided by Descriptive Complexity , 2012, AAAI.

[19]  Kenneth R. Koedinger,et al.  Authoring Tutors with SimStudent: An Evaluation of Efficiency and Model Quality , 2014, Intelligent Tutoring Systems.

[20]  Maya Cakmak,et al.  Towards grounding concepts for transfer in goal learning from demonstration , 2011, 2011 IEEE International Conference on Development and Learning (ICDL).

[21]  John McCarthy,et al.  Programs with common sense , 1960 .

[22]  David J. Mostow,et al.  Machine Transformation of Advice Into a Heuristic Search Procedure , 1983 .

[23]  Çetin Meriçli,et al.  An Interactive Approach for Situated Task Teaching through Verbal Instructions , 2013, AAAI 2013.

[24]  Jerry T. Ball,et al.  A Naturalistic, Functional Approach to Modeling Language Comprehension , 2008, AAAI Fall Symposium: Naturally-Inspired Artificial Intelligence.

[25]  K. A. Ericsson,et al.  Expert and exceptional performance: evidence of maximal adaptation to task constraints. , 1996, Annual review of psychology.

[26]  Michael D. Rychener.  THE INSTRUCTIBLE PRODUCTION SYSTEM: A RETROSPECTIVE ANALYSIS , 1983 .

[27]  Matthias Scheutz,et al.  Tell me when and why to do it! Run-time planner model updates via natural language instruction , 2012, 2012 7th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[28]  Kevin A. Gluck,et al.  Robustness in a variable environment , 2012 .

[29]  Amos Azaria,et al.  Instructable Intelligent Personal Agent , 2016, AAAI.

[30]  Matthew R. Walter,et al.  Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation , 2011, AAAI.

[31]  John E. Laird,et al.  Flexibly Instructable Agents , 1995, J. Artif. Intell. Res..

[32]  John E. Laird,et al.  Learning Goal-Oriented Hierarchical Tasks from Situated Interactive Instruction , 2014, AAAI.

[33]  Jerry R. Hobbs,et al.  Learning by Reading: A Prototype System, Performance Baseline and Lessons Learned , 2007, AAAI.

[34]  Manuela M. Veloso,et al.  Using dialog and human observations to dictate tasks to a learning robot assistant , 2008, Intell. Serv. Robotics.

[35]  John R. Anderson,et al.  Learning to achieve perfect timesharing: architectural implications of Hazeltine, Teague, and Ivry (2002). , 2005, Journal of experimental psychology. Human perception and performance.

[36]  Kenneth D. Forbus,et al.  Exploiting persistent mappings in cross-domain analogical learning of physical domains , 2013, Artif. Intell..

[37]  John E. Laird,et al.  Learning General and Efficient Representations of Novel Games Through Interactive Instruction , 2016 .

[38]  John R. Anderson,et al.  The acquisition of robust and flexible cognitive skills. , 2008, Journal of experimental psychology. General.

[39]  Brian Magerko,et al.  A Conceptual Blending Approach to the Generation of Cognitive Scripts for Interactive Narrative , 2013, Intelligent Narrative Technologies.

[40]  Philip Klahr,et al.  Advice-Taking and Knowledge Refinement: An Iterative View of Skill Acquisition , 1980 .

[41]  Herbert A. Simon,et al.  Artificial Intelligence Systems That Understand , 1977, IJCAI.

[42]  Leo C. Ureel,et al.  Integrating Natural Language, Knowledge Representation and Reasoning, and Analogical Processing to Learn by Reading , 2007, AAAI.

[43]  Kevin A. Gluck,et al.  Mechanisms for Robust Cognition , 2015, Cogn. Sci..

[44]  Kevin A. Gluck,et al.  A quantification of robustness , 2013 .

[45]  Florian Jentsch,et al.  Cognitive Models of Decision Making Processes for Human-Robot Interaction , 2013, HCI.

[46]  Nancy J. Cooke,et al.  The synthetic teammate project , 2009, Comput. Math. Organ. Theory.

[47]  Aaron Mininger,et al.  Interactively Learning Strategies for Handling References to Unseen or Unknown Objects , 2016 .

[48]  Monica N. Nicolescu,et al.  Natural methods for robot task learning: instructive demonstrations, generalization and practice , 2003, AAMAS '03.

[49]  Herbert A Simon,et al.  The understanding process: Problem isomorphs , 1976, Cognitive Psychology.

[50]  Yiannis Demiris,et al.  Hierarchical action learning by instruction through interactive grounding of body parts and proto-actions , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[51]  Michael R. Genesereth,et al.  General Game Playing: Overview of the AAAI Competition , 2005, AI Mag..

[52]  Kenneth D. Forbus,et al.  X Goes First: Teaching Simple Games through Multimodal Interaction , 2014 .

[53]  Christopher W. Myers,et al.  Toward a situation model in a cognitive architecture , 2013, Comput. Math. Organ. Theory.

[54]  Alexander Nareyek,et al.  Game AI is Dead. Long Live Game AI! , 2007, IEEE Intelligent Systems.

[55]  John E. Laird,et al.  The Soar Cognitive Architecture , 2012 .

[56]  John E. Laird,et al.  Learning procedural knowledge through observation , 2001, K-CAP '01.

[57]  Kenneth R. Koedinger,et al.  Predicting Students Performance with SimStudent that Learns Cognitive Skills from Observation , 2007 .

[58]  N. Taatgen.  The nature and transfer of cognitive skills. , 2013, Psychological review.

[59]  Raymond J. Mooney,et al.  Learning to Interpret Natural Language Navigation Instructions from Observations , 2011, Proceedings of the AAAI Conference on Artificial Intelligence.

[60]  Robert J. Crutcher,et al.  The role of deliberate practice in the acquisition of expert performance. , 1993 .

[61]  Jerry T. Ball,et al.  A Bi-Polar Theory of Nominal and Clause Structure and Function , 2004 .

[62]  John R Anderson,et al.  An integrated theory of the mind. , 2004, Psychological review.

[63]  Kenneth R. Koedinger,et al.  When and Why Does Mastery Learning Work: Instructional Experiments with ACT-R "SimStudents" , 2002, Intelligent Tutoring Systems.

[64]  Frank J. Lee,et al.  Does Learning a Complex Task Have to Be Complex?: A Study in Learning Decomposition , 2001, Cognitive Psychology.

[65]  Jim Blythe,et al.  Task learning by instruction in tailor , 2005, IUI.

[66]  H. Simon,et al.  Recall of rapidly presented random chess positions is a function of skill , 1996, Psychonomic bulletin & review.

[67]  John E. Laird,et al.  Acquiring Grounded Representations of Words with Situated Interactive Instruction , 2012 .

[68]  John E. Laird,et al.  Learning Goal Hierarchies from Structured Observations and Expert Annotations , 2004, ILP.

[69]  Miles Merrill.  Where's Massive?: Past, Present and Future for The Lord of the Rings' Crowd Software , 2004 .

[70]  Terry Winograd,et al.  Understanding natural language , 1974 .

[71]  William W. Cohen,et al.  Cognitive anatomy of tutor learning: Lessons learned with SimStudent. , 2013 .

[72]  Christian Lebiere,et al.  Human, Model and Machine: A Complementary Approach to Big Data , 2014, HCBDR '14.

[73]  Jeffrey Mark Siskind,et al.  Learning physically-instantiated game play through visual observation , 2010, 2010 IEEE International Conference on Robotics and Automation.