Hostname: page-component-586b7cd67f-tf8b9 Total loading time: 0 Render date: 2024-11-24T21:44:43.414Z Has data issue: false hasContentIssue false
  • English
  • Français

Learning like a baby: a survey of artificial intelligence approaches

Published online by Cambridge University Press:  12 May 2011

Frank Guerin
Frank Guerin*
Affiliation:
Department of Computing Science, University of Aberdeen, Aberdeen, Scotland; e-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

One of the major stumbling blocks for artificial intelligence remains the commonsense knowledge problem. It is not clear how we could go about building a program which has all the commonsense knowledge of the average human adult. This has led to growing interest in the ‘developmental’ approach, which takes its inspiration from nature (especially the human infant) and attempts to build a program which could develop its own knowledge and abilities through interaction with the world. The challenge here is to find a learning program which can continuously build on what it knows, to reach increasingly sophisticated levels of knowledge. This survey reviews work in this area, with the emphasis on those that focus on early learning, for example, sensorimotor learning. The concluding discussion assesses the progress thus far and outlines some key problems which have yet to be addressed, and whose solution is essential to achieve the goals of the developmental approach.

Type
Articles
Information
The Knowledge Engineering Review , Volume 26 , Issue 2 , 12 May 2011 , pp. 209 - 236
Copyright
Copyright © Cambridge University Press 2011

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Amant, R. S., Morrison, C. T., Chang, Y.-H., Cohen, P. R., Beal, C. R. 2006. An image schema language. In International Conference on Cognitive Modeling, Trieste, Italy, 634–640.Google Scholar
Bakker, B., Schmidhuber, J. 2004. Hierarchical reinforcement learning based on subgoal discovery and subpolicy specialization. In Proceedings of the 8th Conference on Intelligent Autonomous Systems, IAS-8, Amsterdam, The Netherlands, 438–445.Google Scholar
Barto, A. G., Mahadevan, S. 2003. Recent advances in hierarchical reinforcement learning. Discrete Event Dynamic Systems 130(4), 341–379.CrossRefGoogle Scholar
Barto, A. G., Singh, S., Chentanez, N. 2004. Intrinsically motivated learning of hierarchical collections of skills. In Proceedings of International Conference on Developmental Learning (ICDL), Cambridge, MA, 112–119.Google Scholar
Bondu, A., Lemaire, V. 2007. Active learning using adaptive curiosity. In Proceedings of the Seventh International Conference on Epigenetic Robotics, Piscataway, New Jersey.Google Scholar
Brooks, R. A. 1991. Intelligence without representation. Artificial Intelligence 47, 139–159.Google Scholar
Carey, S. 1991. Knowledge acquisition: enrichment or conceptual change? In The Epigenesis of Mind: Essays in Biology and Cognition, Carey, S. & Gelman, R. (eds). Erlbaum, 257–291.Google Scholar
Carey, S. 1992. The origin and evolution of everyday concepts. In Cognitive Models of Science (Minnesota Studies in the Philosophy of Science, Vol. XV), Giere, R. (ed.). University of Minnesota Press, 89–128.Google Scholar
Carey, S. 2004. Bootstrapping and the origins of concepts. Daedalus, Journal of the American Academy of Arts & Sciences Winter, 59–68.Google Scholar
Chang, Y.-H., Cohen, P. R., Morrison, C. T., Amant, R. S., Beal, C. R. 2006. Piagetian adaptation meets image schemas: the jean system. In SAB, Nolfi, S., Baldassarre, G., Calabretta, R., Hallam, J. C. T., Marocco, D., Meyer, J.-A., Miglino, O. & Parisi, D. (eds), Lecture Notes in Computer Science 4095, 369–380. Springer.Google Scholar
Chaput, H. H. 2004. The Constructivist Learning Architecture: A Model of Cognitive Development for Robust Autonomous Robots. PhD thesis, AI Laboratory, The University of Texas at Austin. Supervisors: Kuipers and Miikkulainen.Google Scholar
Cohen, L. B. 1998. An information-processing approach to infant perception and cognition. In The Development of Sensory, Motor, and Cognitive Capacities in Early Infancy, Simion, F. & Butterworth, G. (eds). Psychology Press, 277–300.Google Scholar
Cohen, L. B., Cashon, C. H. 2003. Infant perception and cognition. In Comprehensive Handbook of Psychology. Volume 6, Developmental Psychology. II. Infancy, Lerner, R., Easter-brooks, A. & Mistry, J. (eds). Wiley and Sons, 65–89.Google Scholar
Cohen, P. R., Sutton, C., Burns, B. 2002. Learning effects of robot actions using temporal associations. In The 2nd International Conference on Development and Learning (ICDL'02), Cambridge, Massachusetts, 96–101.Google Scholar
Cohen, P. R., Atkin, M. S., Oates, T., Beal, C. R. 1997. Neo: learning conceptual knowledge by sensorimotor interaction with an environment. In Proceedings of the first International Conference on Autonomous Agents, Marina del Rey, California, 170–177.Google Scholar
Cohen, P. R., Ramoni, M., Sebastiani, P., Warwick, J. 2000. Unsupervised Clustering of Robot Activities: A Bayesian Approach. Technical Report 00-51. University of Massachusetts Computer Science Department.Google Scholar
Cohen, P. R., Chang, Y.-H., Morrison, C. T., Beal, C. R. 2007. Learning and transferring action schemas. In Proceedings of the 20th International Joint Conference on Artificial Intelligence, Hyderabad, India, 720–725.Google Scholar
Colton, S. 2002. Automated Theory Formation in Pure Mathematics. Springer-Verlag.CrossRefGoogle Scholar
Drescher, G. L. 1991. Made-up Minds, A Constructivist Approach to Artificial Intelligence. MIT Press.Google Scholar
Firoiu, L., Cohen, P. R. 1999. Abstracting from robot sensor data using hidden markov models. In Proceedings of the Sixteenth International Conference on Machine Learning, San Francisco, CA, USA, 106–114.Google Scholar
Haith, M. M. 1998. Who put the cog in infant cognition: is rich interpretation too costly? Infant Behavior and Development 21, 167–179.Google Scholar
Hernandez-Gardiol, N., Mahadevan, S. 2000. Hierarchical memory-based reinforcement learning. In Advances in Neural Information Processing Systems (NIPS), Denver Colorado, 1047–1053.Google Scholar
Holmes, M., Isbell, C. 2005. Schema learning: experience-based construction of predictive action models. In Advances in Neural Information Processing Systems (NIPS), Vancouver, B.C., 17, 585–562.Google Scholar
Holmes, M. P., Isbell, C. L., Jr. 2006. Looping suffix tree-based inference of partially observable hidden state. In Proceedings of the 23rd International Conference on Machine Learning, New York, NY, USA, 409–416.Google Scholar
King, G., Oates, T. 2001. The importance of being discrete: learning classes of actions and outcomes through interaction. In Canadian Conference on AI, Stroulia, E. & Matwin, S. (eds), Lecture Notes in Computer Science 2056, 236–245. Springer.Google Scholar
Konidaris, G., Barto, A. 2007. Building portable options: skill transfer in reinforcement learning. In Proceedings of the 20th International Joint Conference on Artificial Intelligence, Hyderabad, India, 895–900.Google Scholar
Konidaris, G., Barto, A. 2008. Sensorimotor abstraction selection for efficient, autonomous robot skill acquisition. In Proceedings of the 7th IEEE International Conference on Development and Learning (ICDL), Monterey, California, 151–156.Google Scholar
Kuipers, B., Beeson, P. 2002. Bootstrap learning for place recognition. In Eighteenth National Conference on Artificial Intelligence, American Association for Artificial Intelligence: Menlo Park, CA, USA, 174–180.Google Scholar
Kuipers, B., Browning, R., Gribble, B., Hewett, M., Remolina, E. 2000. The spatial semantic hierarchy. Artificial Intelligence 119, 191–233.Google Scholar
Kuipers, B., Beeson, P., Modayil, J., Provost, J. 2006. Bootstrap learning of foundational representations. Connection Science 18(2), 145–158.CrossRefGoogle Scholar
Kulakov, A., Stojanov, G. 2002. Structures, inner values, hierarchies and stages: essentials for developmental robot architectures. In Proceedings of the 2nd International Workshop on Epigenetic Robotics – Lund University Cognitive Studies 94, Edinburgh, Scotland, 63–69.Google Scholar
Lakoff, G., Johnson, M. 1980. Metaphors We Live By. University of Chicago Press.Google Scholar
Lee, M. H., Meng, Q., Chao, F. 2007. Staged competence learning in developmental robotics. Adaptive Behavior – Animals, Animats, Software Agents, Robots, Adaptive Systems 15(3), 241–255.Google Scholar
Lungarella, M., Metta, G., Pfeifer, R., Sandini, G. 2003. Developmental robotics: a survey. Connection Science 15(4), 151–190.CrossRefGoogle Scholar
Mandler, J. M. 1992. How to build a baby: II. conceptual primitives. Psychological Review 99(4), 587–604.CrossRefGoogle ScholarPubMed
McGovern, A. 2002. Autonomous Discovery of Temporal Abstractions from Interaction with an Environment. PhD thesis, University of Massachusetts.Google Scholar
Modayil, J., Kuipers, B. J. 2004. Bootstrap learning for object discovery. In IEEE/RSJ International Conference on Intelligent Robots and Systems, Proceedings 1, 742–747.Google Scholar
Modayil, J., Kuipers, B. 2007. Autonomous development of a grounded object ontology by a learning robot. In Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence, Vancouver, British Columbia, Canada, 1095–1101.Google Scholar
Morrison, C. T., Oates, T., King, G. 2001. Grounding the unobservable in the observable: The role and representation of hidden state in concept formation and refinement. In AAAI Spring Symposium on Learning Grounded Representations, Stanford, California, 45–49.Google Scholar
Mugan, J., Kuipers, B. 2008. Continuous-domain reinforcement learning using a learned qualitative state representation. In 22nd International Workshop on Qualitative Reasoning, Boulder, Colorado.Google Scholar
Oates, T., Schmill, M. D., Cohen, P. R. 2000. A method for clustering the experiences of a mobile robot that accords with human judgments. In Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence, Austin, Texas, 846–851.Google Scholar
Olsson, L., Nehaniv, C. L., Polani, D. 2006. From unknown sensors and actuators to actions grounded in sensorimotor perceptions. Connection Science 18(2), 121–144.CrossRefGoogle Scholar
Oudeyer, P.-Y., Kaplan, F., Hafner, V. 2007. Intrinsic motivation systems for autonomous mental development. IEEE Transactions on Evolutionary Computation 11(6), 265–286.CrossRefGoogle Scholar
Perotto, F. S., Álvares, L. O. 2006. Learning regularities with a constructivist agent. In Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems, New York, NY, USA, 807–809.Google Scholar
Perotto, F., Buisson, J., Alvares, L. 2007. Constructivist anticipatory learning mechanism (CALM): dealing with partially deterministic and partially observable environments. In Proceedings of the Seventh International Conference on Epigenetic Robotics, Piscataway, NJ, USA, 117–127.Google Scholar
Piaget, J. 1936. The Origins of Intelligence in Children. Routledge & Kegan Paul.Google Scholar
Piaget, J. 1937. The Construction of Reality in the Child. Routledge & Kegan Paul.Google Scholar
Piaget, J. 1945. Play, Dreams and Imitation in Childhood. Heinemann.Google Scholar
Piaget, J. 1971. Biology and Knowledge. Edinburgh University Press.Google Scholar
Pierce, D., Kuipers, B. 1997. Map learning with uninterpreted sensors and effectors. Artificial Intelligence 92, 169–229.CrossRefGoogle Scholar
Prince, C., Helder, N., Hollich, G. 2005. Ongoing emergence: a core concept in epigenetic robotics. In Proceedings of EpiRob'05 – International Conference on Epigenetic Robotics, Berthouze, L., Kaplan, F., Kozima, H., Yano, H., Konczak, J., Metta, G., Nadel, J., Sandini, G., Stojanov, G. & Balkenius, C. (eds). Lund University Cognitive Studies, 63–70.Google Scholar
Provost, J., Kuipers, B. J., Miikkulainen, R. 2006. Developing navigation behavior through self-organizing distinctive-state abstraction. Connection Science 18(2), 159–172.CrossRefGoogle Scholar
Provost, J., Kuipers, B. J., Miikkulainen, R. 2007. Self-organizing distinctive state abstraction using options. In Proceedings of the Seventh International Conference on Epigenetic Robotics, Piscataway, New Jersey.Google Scholar
Ramoni, M., Sebastiani, P., Cohen, P. 2002. Bayesian clustering by dynamics. Machine Learning 47(1), 91–121.CrossRefGoogle Scholar
Rosenstein, M. T., Cohen, P. R. 1998. Concepts from time series. In Proceedings of the Fifteenth National Conference on Artificial Intelligence AAAI/IAAI, Madison, Wisconsin, 739–745.Google Scholar
Rosenstein, M. T., Cohen, P. R. 1999. Continuous categories for a mobile robot. In Proceedings of the Sixteenth National Conference on Artificial Intelligence AAAI/IAAI, Orlando, Florida, 634–640.Google Scholar
Rosenstein, M. T., Cohen, P. R., Schmill, M. D., Atkin, M. S. 1997. Action representation, prediction and concepts. In Working Notes of the AAAI Workshop on Robots, Softbots, Immobots: Theories of Action, Planning and Control, Providence, Rhode, Island.Google Scholar
Schembri, M., Mirolli, M., Baldassarre, G. 2007a. Evolution and learning in an intrinsically motivated reinforcement learning robot. In Advances in Artificial Life, 9th European Conference, ECAL, e Costa, F. A., Rocha, L. M., Costa, E., Harvey, I. & Coutinho, A., (eds), Lecture Notes in Computer Science 4648, 294–303. Springer.Google Scholar
Schembri, M., Mirolli, M., Baldassarre, G. 2007b. Evolving childhood's length and learning parameters in an intrinsically motivated reinforcement learning robot. In Proceedings of the Seventh International Conference on Epigenetic Robotics, Piscataway, New Jersey.CrossRefGoogle Scholar
Schlesinger, M., Parisi, D. 2001. The agent-based approach: a new direction for computational models of development. Developmental Review 21, 121–146.CrossRefGoogle Scholar
Schmill, M. D., Oates, T., Cohen, P. R. 2000. Learning planning operators in real-world, partially observable environments. In Proceedings of the Fifth International Conference on Artificial Intelligence Planning and Scheduling, Breckenridge, Colorado, 246–253.Google Scholar
Shultz, T. 2003. Computational Developmental Psychology. MIT Press.Google Scholar
Şimşek, O., Barto, A. G. 2006. An intrinsic reward mechanism for efficient exploration. In Proceedings of the 23rd International Conference on Machine Learning, New York, NY, USA, 833–840.Google Scholar
Sinapov, J., Stoytchev, A. 2008. Detecting the functional similarities between tools using a hierarchical representation of outcomes. In Proceedings of the 7th IEEE International Conference on Development and Learning (ICDL), Monterey, CA, 91–96.Google Scholar
Singh, S., Barto, A., Chentanez, N. 2004. Intrinsically motivated reinforcement learning. In 18th Annual Conference on Neural Information Processing Systems (NIPS), Vancouver, B.C., Canada.Google Scholar
Stober, J., Kuipers, B. 2008. From pixels to policies: a bootstrapping agent. In 7th IEEE International Conference on Development and Learning (ICDL-08), Monterey, California, 103–108.Google Scholar
Stojanov, G. 2001. Petitagé: a case study in developmental robotics. In Proceedings of Epigenetic Robotics 1, Balkenius, C., Zlatev, J., Kozima, H., Dautenhahn, K. & Breazeal, C. (eds). Lund University Cognitive Science.Google Scholar
Stojanov, G., Kulakov, A. 2003. Interactivist approach to representation in epigenetic agents. In Proceedings of the Third International Workshop on Epigenetic Robotics, Prince, C. G., Berthouze, L., Kozima, H., Bullock, D., Stojanov, G. & Balkenius, C. (eds). Lund University Cognitive Studies, 123–130.Google Scholar
Stojanov, G., Bozinovski, S., Trajkovski, G. 1997. Interactionist-expectative view on agency and learning. Mathematics and Computers in Simulation 44(3), 295–310.Google Scholar
Stout, A., Konidaris, G. D., Barto, A. G. 2005. Intrinsically motivated reinforcement learning: a promising framework for developmental robot learning. In The AAAI Spring Symposium on Developmental Robotics, Stanford, California.CrossRefGoogle Scholar
Stoytchev, A. 2007. Robot Tool Behavior: A Developmental Approach To Autonomous Tool Use. PhD thesis, College of Computing, Georgia Institute of Technology.Google Scholar
Stracuzzi, D. J. 2005. Scalable Knowledge Acquisition through Memory Organization. Helsinki University of Technology.Google Scholar
Stracuzzi, D. J., Könik, T. 2008. A statistical approach to incremental induction of first-order hierarchical knowledge bases. In Proceedings of the 18th International Conference on Inductive Logic Programming, Berlin, Heidelberg, 279–296.Google Scholar
Stronger, D., Stone, P. 2006. Towards autonomous sensor and actuator model induction on a mobile robot. Connection Science 18(2), 97–119.CrossRefGoogle Scholar
Sutton, R. S. 2006a. The Peak Project. (unpublished document). http://www.cs.ualberta.ca/~sutton/papers/peak-abs.pdfGoogle Scholar
Sutton, R. S. 2006b. Verification, the Key to AI. (unpublished document). http://www.cs.ualberta.ca/~sutton/IncIdeas/KeytoAI.htmlGoogle Scholar
Sutton, R. S., Precup, D., Singh, S. 1999. Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artificial Intelligence 112(1–2), 181–211.CrossRefGoogle Scholar
Turing, A. M. 1950. Computing machinery and intelligence. Mind 59, 433–460.CrossRefGoogle Scholar
Witkowski, M. 1997. Schemes for Learning and Behaviour: A New Expectancy Model. PhD thesis, Department of Computer Science, Queen Mary Westfield College, University of London.Google Scholar
Zlatev, J., Balkenius, C. 2001. Introduction: why ‘epigenetic robotics’? In Epigenetic Robotics 1, Balkenius, C., Zlatev, J., Kozima, H., Dautenhahn, K. & Breazeal, C. (eds). Lund University Cognitive Science.Google Scholar