Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Related Work
Discussion of Results
Limitations and Further Research
Limitations of Tutorial Instruction
Conclusion
References
All Topics
Psychology
Cognitive Science

Flexibly instructable agents

Profile image of John LairdJohn Laird

1995

Abstract

This paper presents an approach to learning from situated, interactive tutorial instruction within an ongoing agent. Tutorial instruction is a exible (and thus powerful) paradigm for teaching tasks because it allows an instructor to communicate whatever types of knowledge an agent might need in whatever situations might arise. To support this exibility, however, the agent must be able to learn multiple kinds of knowledge from a broad range of instructional interactions. Our approach, called situated explanation, achieves such learning through a combination of analytic and inductive techniques. It combines a form of explanation-based learning that is situated for each instruction with a full suite of contextually guided responses to incomplete explanations. The approach is implemented in an agent called Instructo-Soar that learns hierarchies of new tasks and other domain knowledge from interactive natural language instructions. Instructo-Soar meets three key requirements of exible instructability that distinguish it from previous systems: (1) it can take known or unknown commands at any instruction point; (2) it can handle instructions that apply to either its current situation or to a hypothetical situation speci ed in language (as in, for instance, conditional instructions); and (3) it can learn, from instructions, each class of knowledge it uses to perform tasks.

Related papers

Interactive agents learning their environment
Anton Eliëns

Intelligent virtual agents, 2003

In this paper we describe the implementation of interactive agents capable of gathering and extending their knowledge. Interactive agents are designed to perform tasks requested by a user in natural language. Using simple sentences the agent can answer questions and in case a task can not be fulfilled the agent must communicate with the user. In particular, an interactive agent can tell when necessary information for a task is missing, giving the user a chance to supply this information, which may in effect result in teaching the agent. The ...

View PDFchevron_right
Instructible Agents: Software that Just Keeps Getting Better
David Maulsby

Ibm Systems Journal, 1996

Agent software is a topic of growing interest to users and developers in the computer industry. Already, agents and wizards help users automate tasks such as editing and searching for information. But just as we expect human assistants to learn as we work with them, we will also come to expect our computer agents to learn from us. This paper explores the idea of an instructible agent that can learn both from examples and from advice. To understand design issues and languages for human-agent communication, we first describe an experiment that simulates the behavior ofsuch an agent. Then we describe some implemented and ongoing instructible agent projects in text and graphic editing, World Wide Web browsing, and virtual reality. Finally, we analyze the trade-offs involved in agent software and argue that instructible agents represent a "sweet spot" in the trade-off between convenience and control.

View PDFchevron_right
Agents that Learn to Instruct
Lewis Johnson

1997

This paper describes a software agent that learns procedural knowledge from a human instructor well enough to teach human students. In order to teach, the agent needs more than the ability to perform a procedure. It must also be able to monitor human students performing the procedure and be able to articulate the reasons why actions are necessary. Our research concentrates on helping an instructor instruct the agent in a natural manner, on reducing the burden on the instructor, and on focusing learning on the procedure being taught. Initially the agent has little domain knowledge. The instructor demonstrates a procedure by directly manipulating a simulated environment. However, one demonstration is not sufficient for understanding the causal relationships between a demonstration's actions. Unfortunately, the more demonstrations a procedure requires, the greater the instructor's burden. However, fewer demonstrations can be required if the agent autonomously experiments. Our experiments attempt to understand the causal dependencies between a demonstration's actions by perturbing the order of the demonstration's actions.

View PDFchevron_right
A system for interactive learning in dialogue with a tutor
Danijel Markovic

2011

In this paper we present representations and mechanisms that facilitate continuous learning of visual concepts in dialogue with a tutor and show the implemented robot system. We present how beliefs about the world are created by processing visual and linguistic information and show how they are used for planning system behaviour with the aim at satisfying its internal drive -to extend its knowledge. The system facilitates different kinds of learning initiated by the human tutor or by the system itself. We demonstrate these principles in the case of learning about object colours and basic shapes.

View PDFchevron_right
Incorporating tutorial strategies into an intelligent assistant
Charles Rich

Proceedings of the 6th international conference on Intelligent user interfaces - IUI '01, 2001

Computer tutors and intelligent software assistants have traditionally been thought of as different kinds of systems. However tutors and assistants share many properties. We have incorporated tutorial strategies into an intelligent assistant based on the COLLAGEN architecture. We are working on an agent, named Triton, which teaches and helps users with the graphical user interface of an air travel planning system. We found that the collaborative model underlying COLLAGEN is an excellent foundation for both an assistant and a tutor, and that both modes of interaction can be implemented in the same system with different parameter settings.

View PDFchevron_right
E-TUTOR: a tutoring agent
Ricardo Ribeiro

Abstract. In this paper we describe E-TUTOR, a platform for animated tutoring agents that takes as input spoken or written utterances and outputs its answers in text and speech forms. The agent is animated within a game environment and its answers are synchronized with its mouth/lips movements. A Natural Language Understanding module implements several Natural Language Processing and Machine Learning techniques. The E-TUTOR is currently being tested in Monserrate, answering questions about the palace.

View PDFchevron_right
A Tutoring Based Approach to the Development of Intelligent Agents
Gheorghe Tecuci, Mihai Boicu

International Series in Intelligent Technologies, 2000

This chapter introduces the concept of intelligent agent, analyses some of the issues and trends in developing them and presents a specific agent development approach. The presented approach, called Disciple, relies on importing ontologies from existing repositories of knowledge, and on teaching the agent how to perform various tasks, in a way that resembles how an expert would teach a human apprentice when solving problems in cooperation.

View PDFchevron_right
A Cognitive Tutoring Agent with Automatic Reasoning Capabilities
Philippe Fournier-Viger, Andre Mayers

2011

To build an intelligent tutoring system, a key task is to define an expertise model that can support appropriate tutoring services. However, for some ill-defined domains, classical approaches for representing expertise do not work well. To address this issue, we illustrate in this paper a novel approach which is to combine several approaches into a hybrid model to support tutoring services in procedural and ill-defined domains. We illustrate this idea in a tutoring system for operating Canadarm2, a robotic arm installed on the international space station. To support tutoring services in this ill-defined domain, we have developed a model combining three approaches: (1) a data mining approach for automatically building a task model from user solutions, (2) a cognitive model to cover well-defined parts of the task and spatial reasoning, (3) and a 3D path-planner to cover all other aspects of the task. Experimental results show that the hybrid model allows providing assistance to learners that is much richer than what could be offered by each individual approach.

View PDFchevron_right
Disciple-COA: From Agent Programming to Agent Teaching
Mihai Boicu

Proceedings of the Seventeenth International Conference on Machine Learning, 2000

This paper presents Disciple-COA, the most recent learning agent shell developed in the Disciple framework that aims at changing the way an intelligent agent is built: from "being programmed" by a knowledge engineer, to "being taught" by a domain expert. Disciple-COA can collaborate with the expert to develop its knowledge base consisting of a frame-based ontology that defines the terms from the application domain, and a set of plausible version space rules expressed with these terms. Its central component is a plausible reasoner that can distinguish between four types of problem solving situations: routine, innovative, inventive and creative. This ability guides the interactions with the expert during which the agent learns general rules from specific examples, by integrating a wide range of knowledge acquisition and machine learning strategies, including apprenticeship learning, empirical inductive learning from examples and explanations, and analogical learning. Disciple-COA was developed in the DARPA's High Performance Knowledge Bases program to solve the challenge problem of critiquing military courses of action that were developed as hasty candidate plans for ground combat operations. We present the course of action challenge problem, the process of teaching Disciple-COA to solve it, and the results of DARPA's evaluation in which Disciple-COA demonstrated the best knowledge acquisition rate and problem solving performance. We also present a separate knowledge acquisition experiment conducted at the Battle Command Battle Lab where experts with no prior knowledge engineering experience succeeded to rapidly teach Disciple-COA to correctly critique courses of action.

View PDFchevron_right
Agents for integrated tutoring in spoken dialogue systems
Jaakko Hakulinen

2003

In this paper, we introduce the concept of integrated tutoring in speech applications. An integrated tutoring system teaches the use of a system to a user while he/she is using the system in a typical manner. Furthermore, we introduce the general principles of how to implement applications with integrated tutoring agents and present an example implementation for an existing e-mail system. The main innovation of the approach is that the tutoring agents are part of the application, but implemented in a way which makes it possible to plug them into the system without modifying it. This is possible due to a set of small, stateless agents and a shared Information Storage provided by our system architecture. Integrated tutoring agents are easily expandable and configurable, and general agents can be shared between applications. We have also received positive feedback about integrated tutoring in initial user tests conducted with the implementation.

View PDFchevron_right

References (108)

  1. Akatsuka, N. (1986). Conditionals are discourse-bound. In Traugott, E. C. (Ed.), On Conditionals, pp. 333{51. Cambridge Univ. Press, Cambridge.
  2. Alterman, R., Zito-Wolf, R., & Carpenter, T. (1991). Interaction, comprehension, and instruction usage. Journal of the Learning Sciences, 1(3&4), 273{318.
  3. Anderson, J. R. (1983). The architecture of cognition. Harvard University Press, Cambridge, MA. Bergadano, F., & Giordana, A. (1988). A knowledge intensive approach to concept in- duction. In Proceedings of the International Conference on Machine Learning, pp. 305{317.
  4. Birmingham, W., & Klinker, G. (1993). Knowledge acquisition tools with explicit problem- solving methods. The Knowledge Engineering Review, 8(1).
  5. Birmingham, W., & Siewiorek, D. (1989). Automated knowledge acquisition for a computer hardware synthesis system. Knowledge Acquisition, 1, 321{340.
  6. Bloom, B. S. (1984). The 2 sigma problem: The search for methods of group instruction as e ective as one-to-one tutoring. Educational Researcher, 13(6), 4{16.
  7. Brachman, R. J. (1980). An introduction to KL-ONE. In Brachman, R. J. (Ed.), Research in Natural Language Understanding, pp. 13{46. Bolt, Beranek and Newman Inc., Cambridge, MA.
  8. Carbonell, J. G., & Gil, Y. (1987). Learning by experimentation. In Proceedings of the International Workshop on Machine Learning, pp. 256{265.
  9. Carbonell, J. G., Michalski, R. S., & Mitchell, T. M. (1983). An overview of machine learning. In Michalski, R. S., Carbonell, J. G., & Mitchell, T. M. (Eds.), Machine Learning: An arti cial intelligence approach. Morgan Kaufmann.
  10. Carpenter, T., & Alterman, R. (1994). A reading agent. In Proceedings of the Twelfth National Conference on Arti cial Intelligence Seattle, WA.
  11. Chapman, D. (1990). Vision, Instruction, and Action. Ph.D. thesis, Massachusetts Institute of Technology, Arti cial Intelligence Laboratory.
  12. Chi, M. T. H., Bassok, M., Lewis, M. W., Reimann, P., & Glaser, R. (1989). Self- explanations: How students study and use examples in learning to solve problems. Cognitive Science, 13, 145{182.
  13. Cypher, A. (Ed.). (1993). Watch what I do: Programming by demonstration. MIT Press, Cambridge, Mass.
  14. Davis, R. (1979). Interactive transfer of expertise: Acquisition of new inference rules. Arti cial Intelligence, 12(2), 409{427.
  15. DeJong, G. F., & Mooney, R. J. (1986). Explanation-based learning: An alternative view. Machine Learning, 1(2), 145{176.
  16. Dent, L., Boticario, J., McDermott, J., Mitchell, T., & Zabowski, D. (1992). A personal learning apprentice. In Proceedings of the International Joint Conference on Arti cial Intelligence.
  17. DiEugenio, B. (1993). Understanding natural language instructions: A computational ap- proach to purpose clauses. Ph.D. thesis, University of Pennsylvania. IRCS Report 93-52.
  18. DiEugenio, B., & Webber, B. (1992). Plan recognition in understanding instructions. In Hendler, J. (Ed.), Proceedings of the First International Conference on Arti cial In- telligence Planning Systems, pp. 52{61 College Park, MD.
  19. Donoho, S. K., & Wilkins, D. C. (1994). Exploiting the ordering of observed problem-solving steps for knowledge ase re nement: An apprenticeship approach. In Proceedings of the 12th National Conference on Arti cal Intelligence Seattle, WA.
  20. Drummond, M. (1989). Situated control rules. In Proceedings of the First International Con- ference on Principles of Knowledge Representation Toronto, Canada. Morgan Kauf- mann.
  21. Emihovich, C., & Miller, G. E. (1988). Talking to the turtle: A discourse analysis of Logo instruction. Discourse Processes, 11, 183{201.
  22. Eshelman, L., Ehret, D., McDermott, J., & Tan, M. (1987). MOLE: A tenacious knowledge- acquisition tool. International Journal of Man-Machine Studies, 26(1), 41{54.
  23. Fikes, R. E., Hart, P. E., & Nilsson, N. J. (1972). Learning and executing generalized robot plans. Arti cial Intelligence, 3, 251{288.
  24. Ford, C. A., & Thompson, S. A. (1986). Conditionals in discourse: A text-based study from English. In Traugott, E. C. (Ed.), On Conditionals, pp. 353{72. Cambridge Univ. Press, Cambridge.
  25. Frederking, R. E. (1988). Integrated natural language dialogue: A computational model. Kluwer Academic Press, Boston.
  26. Golding, A., Rosenbloom, P. S., & Laird, J. E. (1987). Learning search control from outside guidance. In Proceedings of the Tenth International Joint Conference on Arti cial Intelligence, pp. 334{337.
  27. Grosz, B. J. (1977). The Representation and use of focus in dialogue understanding. Ph.D. thesis, University of California, Berkeley.
  28. Gruber, T. (1989). Automated knowledge acquisition for strategic knowledge. Machine Learning, 4(3-4), 293{336.
  29. Guha, R. V., & Lenat, D. B. (1990). Cyc: A mid-term report. AI Magazine, 11(3), 32{59.
  30. Haas, N., & Hendrix, G. G. (1983). Learning by being told: Acquiring knowledge for information management. In Michalski, R. S., Carbonell, J. G., & Mitchell, T. M. (Eds.), Machine Learning: An arti cial intelligence approach. Morgan Kaufmann.
  31. Haiman, J. (1978). Conditionals are topics. Language, 54, 564{89.
  32. Hall, R. J. (1988). Learning by failing to explain. Machine Learning, 3(1), 45{77.
  33. Hayes-Roth, F., Klahr, P., & Mostow, D. J. (1981). Advice taking and knowledge re nement: An iterative view of skill acquisition. In Anderson, J. R. (Ed.), Cognitive skills and their acquisition, pp. 231{253. Lawrence Erlbaum Associates, Hillsdale, NJ.
  34. Hu man, S. B. (1994). Instructable autonomous agents. Ph.D. thesis, University of Michi- gan, Dept. of Electrical Engineering and Computer Science.
  35. Hu man, S. B., & Laird, J. E. (1992). Dimensions of complexity in learning from interactive instruction. In Erickson, J. (Ed.), Proceedings of Cooperative Intelligent Robotics in Space III, SPIE Volume 1829.
  36. Hu man, S. B., & Laird, J. E. (1993). Learning procedures from interactive natural lan- guage instructions. In Utgo , P. (Ed.), Machine Learning: Proceedings of the Tenth International Conference.
  37. Hu man, S. B., & Laird, J. E. (1994). Learning from highly exible tutorial instruction. In Proceedings of the 12th National Conference on Arti cial Intelligence (AAAI-94)
  38. Seattle, WA.
  39. Hu man, S. B., Miller, C. S., & Laird, J. E. (1993). Learning from instruction: A knowledge- level capability within a uni ed theory of cognition. In Proceedings of the Fifteenth Annual Conference of the Cognitive Science Society, pp. 114{119.
  40. Johnson-Laird, P. N. (1986). Conditionals and mental models. In Traugott, E. C. (Ed.), On Conditionals. Cambridge Univ. Press, Cambridge.
  41. Jones, R. M., Tambe, M., Laird, J. E., & Rosenbloom, P. S. (1993). Intelligent auto- mated agents for ight training simulators. In Proceedings of the Third Conference on Computer Generated Forces, pp. 33{42 Orlando, FL.
  42. Just, M. A., & Carpenter, P. A. (1976). Verbal comprehension in instructional situations. In Klahr, D. (Ed.), Cognition and Instruction. Lawrence Erlbaum Associates, Hillsdale, NJ.
  43. Kieras, D. E., & Bovair, S. (1984). The role of a mental model in learning to operate a device. Cognitive Science, 8, 255{273.
  44. Kodrato , Y., & Tecuci, G. (1987a). DISCIPLE-1: Interactive apprentice system in weak theory elds. In Proceedings of the Tenth International Joint Conference on Arti cial Intelligence, pp. 271{273.
  45. Kodrato , Y., & Tecuci, G. (1987b). Techniques of design and DISCIPLE learning appren- tice. International Journal of Expert Systems, 1(1), 39{66.
  46. Laird, J. E., Congdon, C. B., Altmann, E., & Doorenbos, R. (1993). Soar user's manual, version 6..
  47. Laird, J. E., Hucka, M., Yager, E. S., & Tuck, C. M. (1990). Correcting and extending domain knowledge using outside guidance. In Proceedings of the Seventh International Conference on Machine Learning.
  48. Laird, J. E., Newell, A., & Rosenbloom, P. S. (1987). Soar: An architecture for general intelligence. Arti cial Intelligence, 33(1), 1{64.
  49. Laird, J. E., & Rosenbloom, P. S. (1990). Integrating execution, planning, and learning in Soar for external environments. In Proceedings of the Eighth National Conference on Arti cial Intelligence, pp. 1022{1029. AAAI Press.
  50. Lewis, C. (1988). Why and how to learn why: Analysis-based generalization of procedures. Cognitive Science, 12, 211{256.
  51. Lewis, R. L. (1993). An Architecturally-Based Theory of Human Sentence Comprehension. Ph.D. thesis, Carnegie Mellon University, School of Computer Science.
  52. Lewis, R. L., Newell, A., & Polk, T. A. (1989). Toward a Soar theory of taking instruc- tions for immediate reasoning tasks. In Proceedings of the Annual Conference of the Cognitive Science Society.
  53. Lindsay, R. K. (1963). Inferential memory as the basis of machines which understand natural language. In Feigenbaum, E. A., & Feldman, J. (Eds.), Computers and Thought, pp. 217{233. R. Oldenbourg KG.
  54. Maes, P. (1994). Agents that reduce work and information overload. Communications of the ACM, 37(7).
  55. Maes, P., & Kozierok, R. (1993). Learning interface agents. In Proceedings of the National Conference on Arti cial Intelligence, pp. 459{465.
  56. Mann, W. C., & Thompson, S. A. (1988). Rhetorical structure theory: Toward a functional theory of text organization. Text, 8(3), 243{281.
  57. Marcus, S., & McDermott, J. (1989). SALT: A knowledge acquisition language for propose- and-revise systems. Arti cial Intelligence, 39(1), 1{37.
  58. Martin, C. E., & Firby, R. J. (1991). Generating natural language expectations from a reactive execution system. In Proceedings of the Thirteenth Annual Conference of the Cognitive Science Society, pp. 811{815.
  59. McCarthy, J. (1968). The advice taker. In Minsky, M. (Ed.), Semantic Information Pro- cessing, pp. 403{410. MIT Press, Cambridge, Mass.
  60. Miller, C. M. (1993). A model of concept acquisition in the context of a uni ed theory of cognition. Ph.D. thesis, The University of Michigan, Dept. of Computer Science and Electrical Engineering.
  61. Minton, S., Carbonell, J. G., Knoblock, C. A., Kuokka, D. R., Etzioni, O., & Gil, Y. (1989). Explanation-based learning: A problem-solving perspective. Arti cial Intelligence, 40, 63{118.
  62. Mitchell, T., Caruana, R., Freitag, D., McDermott, J., & Zabowski, D. (1994). Experience with a learning personal assistant. Communications of the ACM, 37(7).
  63. Mitchell, T. M., Keller, R. M., & Kedar-Cabelli, S. T. (1986). Explanation-based general- ization: A unifying view. Machine Learning, 1.
  64. Mitchell, T. M., Mahadevan, S., & Steinberg, L. I. (1990). LEAP: A learning apprentice system for VLSI design. In Kodrato , Y., & Michalski, R. S. (Eds.), Machine Learning: An arti cial intelligence approach, Vol. III. Morgan Kaufmann.
  65. Mooney, R. J. (1990). Learning plan schemata from observation: Explanation-based learn- ing for plan recognition. Cognitive Science, 14, 483{509.
  66. Mostow, D. J. (1983). Learning by being told: Machine transformation of advice into a heuristic search procedure. In Michalski, R. S., Carbonell, J. G., & Mitchell, T. M. (Eds.), Machine Learning: An arti cial intelligence approach. Morgan Kaufmann.
  67. Musen, M. A. (1989). Automated support for building and extending expert models. Ma- chine Learning, 4(3-4), 347{376.
  68. Newell, A. (1981). The knowledge level. AI Magazine, 2(2), 1{20.
  69. Newell, A. (1990). Uni ed Theories of Cognition. Harvard University Press, Cambridge, Massachusetts.
  70. Newell, A., Yost, G., Laird, J. E., Rosenbloom, P. S., & Altmann, E. (1990). Formulating the problem space computational model. In Proceedings of the 25th Anniversary Symposium, School of Computer Science, Carnegie Mellon University.
  71. Pazzani, M. (1991a). A computational theory of learning causal relationships. Cognitive Science, 15, 401{424.
  72. Pazzani, M. (1991b). Learning to predict and explain: An integration of similarity-based, theory driven, and explanation-based learning. Journal of the Learning Sciences, 1(2), 153{199.
  73. Pearson, D. J., & Hu man, S. B. (1995). Combining learning from instruction with recovery from incorrect knowledge. In Gordon, D., & Shavlik, J. (Eds.), Proceedings of the 1995 Machine Learning Workshop on Agents that Learn from Other Agents.
  74. Pearson, D. J., Hu man, S. B., Willis, M. B., Laird, J. E., & Jones, R. M. (1993). A symbolic solution to intelligent real-time control. IEEE Robotics and Autonomous Systems, 11, 279{291.
  75. Pearson, D. J., & Laird, J. E. (1995). Toward incremental knowledge correction for agents in complex environments. In Muggleton, S., Michie, D., & Furukawa, K. (Eds.), Machine Intelligence, Vol. 15. Oxford University Press.
  76. Porter, B. W., Bareiss, R., & Holte, R. C. (1990). Concept learning and heuristic classi - cation in weak-theory domains. Arti cial Intelligence, 45(3), 229{263.
  77. Porter, B. W., & Kibler, D. F. (1986). Experimental goal regression: A method for learning problem-solving heuristics. Machine Learning, 1, 249{286.
  78. Redmond, M. A. (1992). Learning by observing and understanding expert problem solving. Ph.D. thesis, Georgia Institute of Technology.
  79. Rosenbloom, P. S., & Aasman, J. (1990). Knowledge level and inductive uses of chunking (EBL). In Proceedings of the National Conference on Arti cial Intelligence.
  80. Rosenbloom, P. S., & Laird, J. E. (1986). Mapping explanation-based generalization onto Soar. In Proceedings of the National Conference on Arti cial Intelligence, pp. 561{567.
  81. Rosenbloom, P. S., Laird, J. E., & Newell, A. (1988). The chunking of skill and knowledge. In Bouma, H., & Elsendoorn, A. G. (Eds.), Working Models of Human Perception, pp. 391{410. Academic Press, London, England.
  82. Rosenbloom, P. S., Laird, J. E., & Newell, A. (Eds.). (1993a). The Soar Papers: Research on integrated intelligence. MIT Press, Cambridge, Mass.
  83. Rosenbloom, P. S., Laird, J. E., & Newell, A. (Eds.). (1993b). The Soar Papers: Research on integrated intelligence. MIT Press, Cambridge, Mass.
  84. Rosenbloom, P. S., & Newell, A. (1986). The chunking of goal hierarchies: A generalized model of practice. In Michalski, R. S., Carbonell, J. G., & Mitchell, T. M. (Eds.), Machine Learning: An arti cial intelligence approach, Volume II. Morgan Kaufmann.
  85. Rumelhart, D. E., & McClelland, J. L. (Eds.). (1986). Parallel distributed processing: Ex- plorations in the microstructure of cognition. MIT Press, Cambridge, MA.
  86. Rychener, M. D. (1983). The instructible production system: A retrospective analysis. In Michalski, R. S., Carbonell, J. G., & Mitchell, T. M. (Eds.), Machine Learning: An arti cial intelligence approach, pp. 429{460. Morgan Kaufmann.
  87. Sandberg, J., & Wielinga, B. (1991). How situated is cognition?. In Proceedings of the International Joint Conference on Arti cial Intelligence, pp. 341{346.
  88. Schank, R. C. (1975). Conceptual Information Processing. American Elsevier, New York.
  89. Schank, R. C., & Leake, D. B. (1989). Creativity and learning in a case-based explainer. Arti cial Intelligence, 40, 353{385.
  90. Segre, A. M. (1987). A learning apprentice system for mechanical assembly. In Third IEEE Conference on Arti cial Intelligence for Applications, pp. 112{117.
  91. Shen, W. (1993). Discovery as autonomous learning from the environment. Machine Learn- ing, 12, 143{165.
  92. Simon, H. A. (1977). Arti cial intelligence systems that understand. In Proceedings of the Fifth International Joint Conference on Arti cial Intelligence, pp. 1059{1073.
  93. Simon, H. A., & Hayes, J. R. (1976). Understanding complex task instructions. In Klahr, D. (Ed.), Cognition and Instruction. Lawrence Erlbaum Associates, Hillsdale, NJ.
  94. Singley, M. K., & Anderson, J. R. (1989). The transfer of cognitive skill. Harvard University Press.
  95. Sutton, R. S., & Pinette, B. (1985). The learning of world models by connectionist networks. In Proceedings of the Seventh Annual Conference of the Cognitive Science Society, pp. 54{64.
  96. Thrun, S. B., & Mitchell, T. M. (1993). Integrating inductive neural network learning and explanation-based learning. In Proceedings of the International Joint Conference on Arti cial Intelligence, pp. 930{936.
  97. VanLehn, K. (1987). Learning one subprocedure per lesson. Arti cial Intelligence, 31(1), 1{40.
  98. VanLehn, K., Ball, W., & Kowalski, B. (1990). Explanation-based learning of correctness: Towards a model of the self-explanation e ect. In Proceedings of the 12th Annual Conference of the Cognitive Science Society, pp. 717{724.
  99. VanLehn, K., & Jones, R. (1991). Learning physics via explanation-based learning of cor- rectness and analogical search control. In Proceedings of the International Machine Learning Workshop.
  100. VanLehn, K., Jones, R. M., & Chi, M. T. H. (1992). A model of the self-explanation e ect. Journal of the Learning Sciences, 2(1), 1{59.
  101. Vere, S., & Bickmore, T. (1990). A basic agent. Computational Intelligence, 6, 41{60.
  102. Wertsch, J. V. (1979). From social interaction to higher psychological processes: A clari - cation and application of Vygotsky's theory. Human Development, 22, 1{22.
  103. Widmer, G. (1989). A tight integration of deductive and inductive learning. In Proceedings of the International Workshop on Machine Learning, pp. 11{13.
  104. Wilkins, D. C. (1990). Knowledge base re nement as improving an incomplete and incorrect domain theory. In Kodrato , Y., & Michalski, R. S. (Eds.), Machine Learning: An Arti cial Intelligence Approach, Volume III, pp. 493{514. Morgan Kaufmann.
  105. Winograd, T. (1972). Understanding Natural Language. Academic Press, New York.
  106. Wood, D., Bruner, J. S., & Ross, G. (1976). The role of tutoring in problem solving. Journal of Child Psychology and Psychiatry, 17, 89{100.
  107. Yost, G. R. (1993). Acquiring knowledge in Soar. IEEE Expert, 8(3), 26{34.
  108. Yost, G. R., & Newell, A. (1989). A problem space approach to expert system speci cation. In Proceedings of the International Joint Conference on Arti cial Intelligence, pp. 621{7.

Related papers

Learning Task Formulations through Situated Interactive Instruction
John Laird

2013

We present an agent, called RosieTAG, which is implemented in Soar and interacts with an external robotic environment. Rosie learns new games through interactive instruction with a human via restricted natural language. Instead of learning policy or strategy information as is common in other game learners, Rosie learns multiple game formulations (the objects, players, and rules of a game) and then uses its own general strategies to solve them. We describe the structure and functionality of Rosie, and evaluate its competence, generality, communication efficiency, communication accessibility, and ability to continuously learn and accumulate new tasks and new task knowledge.

View PDFchevron_right
Towards Situated, Interactive, Instructable Agents in a Cognitive Architecture
John Laird

2011

This paper discusses the challenge of designing instructable agents that can learn through interaction with a human expert. Learning through instruction is a powerful paradigm for acquiring knowledge because it limits the complexity of the learning task in a variety of ways. To support learning through instruction, the agent must be able to effectively communicate its lack of knowledge to the human, comprehend instructions, and apply them to the ongoing task. We identify some problems of concern when designing instructable agents. We propose an agent design that addresses some of these problems. We instantiate this design in the Soar cognitive architecture and analyze its capabilities on a learning task.

View PDFchevron_right
Learning Goal-Oriented Hierarchical Tasks from Situated Interactive Instruction
John Laird

Our research aims at building interactive robots and agents that can expand their knowledge by interacting with human users. In this paper, we focus on learning goal-oriented tasks from situated interactive instructions. Learning the structure of novel tasks and how to execute them is a challenging computational problem requiring the agent to acquire a variety of knowledge including goal definitions and hierarchical control information. We frame acquisition of novel tasks as an explanation-based learning (EBL) problem and propose an interactive learning variant of EBL for a robotic agent. We show that our approach can exploit information in situated instructions along with the domain knowledge to demonstrate fast generalization on several tasks. The knowledge acquired transfers across structurally similar tasks. Finally, we show that our approach seamlessly combines agent-driven exploration with instructions for mixed-initiative learning.

View PDFchevron_right
Learning Task Formulations through Situated Interactive
John Laird

2013

We present an agent, called RosieTAG, which is implemented in Soar and interacts with an external robotic environment. Rosie learns new games through interactive instruction with a human via restricted natural language. Instead of learning policy or strategy information as is common in other game learners, Rosie learns multiple game formulations (the objects, players, and rules of a game) and then uses its own general strategies to solve them. We describe the structure and functionality of Rosie, and evaluate its competence, generality, communication efficiency, communication accessibility, and ability to continuously learn and accumulate new tasks and new task knowledge.

View PDFchevron_right
Learning procedures from interactive natural language instructions
John Laird

1994

Despite its ubiquity in human learning, very little work has been done in artificiaJ intelligence on agents that learn from interactive natural language instructions. In this paper, we examine the problem of learning procedures from interactive, situated instruction, in which the student is attempting to perform tasks within the instructional domain, and asks for instruction when it is needed. We present Instructo-Soar, a system that behaves and learns in response to interactive natural language instructions. Instructo-Soar learns completely new procedures from sequences of instruction, and also learns how to extend its knowledge of previously known procedures to new situations. These learning tasks require both inductive and analytic learning, lnstructo-Soar exhibits a multiple execution learning process in which initial learning has a rote, episodic flavor, and later executions allow the initially learned knowledge to be generalized properly.

View PDFchevron_right

Related topics

  • Cognitive Science
  • Applied Mathematics
  • Artificial Intelligence
  • Approaches to Learning
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved