Learning like a baby: a survey of artificial intelligence approaches

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.

[1]  Simon Colton,et al.  Automated Theory Formation in Pure Mathematics , 2002, Distinguished dissertations.

[2]  Mark H. Lee,et al.  Staged Competence Learning in Developmental Robotics , 2007, Adapt. Behav..

[3]  Paul R. Cohen,et al.  Unsupervised Clustering of Robot Activitie: A Bayesian Approach TITLE2: , 2000 .

[4]  J. Piaget,et al.  The Origins of Intelligence in Children , 1971 .

[5]  Marco Mirolli,et al.  Evolution and Learning in an Intrinsically Motivated Reinforcement Learning Robot , 2007, ECAL.

[6]  Chrystopher L. Nehaniv,et al.  From unknown sensors and actuators to actions grounded in sensorimotor perceptions , 2006, Connect. Sci..

[7]  S. Carey,et al.  The Epigenesis of mind : essays on biology and cognition , 1991 .

[8]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[9]  Benjamin Kuipers,et al.  Continuous-domain reinforcement learning using a learned qualitative state representation , 2008 .

[10]  Peter Stone,et al.  Towards autonomous sensor and actuator model induction on a mobile robot , 2006, Connect. Sci..

[11]  J. Sinapov,et al.  Detecting the functional similarities between tools using a hierarchical representation of outcomes , 2008, 2008 7th IEEE International Conference on Development and Learning.

[12]  Gary W. King,et al.  The Importance of Being Discrete: Learning Classes of Actions and Outcomes through Interaction , 2001, AI.

[13]  Benjamin Kuipers,et al.  Map Learning with Uninterpreted Sensors and Effectors , 1995, Artif. Intell..

[14]  Sridhar Mahadevan,et al.  Recent Advances in Hierarchical Reinforcement Learning , 2003, Discret. Event Dyn. Syst..

[15]  M. Haith.  Who put the cog in infant cognition ? Is rich interpretation too costly ? , 1998 .

[16]  J. Piaget.  The construction of reality in the child , 1954 .

[17]  Benjamin Kuipers,et al.  Bootstrap learning for object discovery , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[18]  Andrew G. Barto,et al.  An intrinsic reward mechanism for efficient exploration , 2006, ICML.

[19]  Paul R. Cohen,et al.  Unsupervised clustering of robot activities: a Bayesian approach , 2000, AGENTS '00.

[20]  Clayton T. Morrison,et al.  Piagetian Adaptation Meets Image Schemas: The Jean System , 2006, SAB.

[21]  Benjamin Kuipers,et al.  The Spatial Semantic Hierarchy , 2000, Artif. Intell..

[22]  Paul R. Cohen,et al.  Learning Planning Operators in Real-World, Partially Observable Environments , 2000, AIPS.

[23]  T. Oates,et al.  Grounding the Unobservable in the Observable: The Role and Representation of Hidden State in Concept Formation and Refinement , 2001 .

[24]  Bram Bakker,et al.  Hierarchical Reinforcement Learning Based on Subgoal Discovery and Subpolicy Specialization , 2003 .

[25]  A. Olding.  Biology and knowledge , 2008 .

[26]  Benjamin Kuipers,et al.  Bootstrap learning for place recognition , 2002, AAAI/IAAI.

[27]  Nuttapong Chentanez,et al.  Intrinsically Motivated Learning of Hierarchical Collections of Skills , 2004 .

[28]  Paul R. Cohen,et al.  Learning effects of robot actions using temporal associations , 2002, Proceedings 2nd International Conference on Development and Learning. ICDL 2002.

[29]  Charles Lee Isbell,et al.  Looping suffix tree-based inference of partially observable hidden state , 2006, ICML.

[30]  Giulio Sandini,et al.  Developmental robotics: a survey , 2003, Connect. Sci..

[31]  Marco Mirolli,et al.  Evolving Childhood's Length and Learning Parameters in an Intrinsically Motivated Reinforcement Learning Robot , 2007 .

[32]  Georgi Stojanov,et al.  Structures, inner values, hierarchies and stages: essentials for developmental robot architectures , 2002 .

[33]  Benjamin Kuipers,et al.  Autonomous Development of a Grounded Object Ontology by a Learning Robot , 2007, AAAI.

[34]  B. Kuipers,et al.  From pixels to policies: A bootstrapping agent , 2008, 2008 7th IEEE International Conference on Development and Learning.

[35]  Leslie B. Cohen,et al.  Infant Perception and Cognition , 2010 .

[36]  Stevo Bozinovski,et al.  Interactionist-expectative view on agency and learning , 1997 .

[37]  J. Piaget.  Play, dreams and imitation in childhood , 1951 .

[38]  Andrew G. Barto,et al.  Intrinsically Motivated Reinforcement Learning: A Promising Framework for Developmental Robot Learning , 2005 .

[39]  Clayton T. Morrison,et al.  Learning and Transferring Action Schemas , 2007, IJCAI.

[40]  Benjamin Kuipers,et al.  Bootstrap learning of foundational representations , 2006, Connect. Sci..

[41]  C. G. Prince,et al.  Ongoing Emergence:A Core Concept in Epigenetic Robotics , 2005 .

[42]  G. Konidaris,et al.  Sensorimotor abstraction selection for efficient, autonomous robot skill acquisition , 2008, 2008 7th IEEE International Conference on Development and Learning.

[43]  T. Shultz.  Computational Developmental Psychology , 2003 .

[44]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[45]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[46]  Amy McGovern.  Autonomous Discovery of Abstractions through Interaction with an Environment , 2002, SARA.

[47]  S. Carey.  Knowledge Acquisition: Enrichment or Conceptual Change? , 1991 .

[48]  Giulio Sandini,et al.  Proceedings of the Fourth International Workshop on Epigenetic Robotics , 2004 .

[49]  D. Parisi,et al.  The Agent-Based Approach: A New Direction for Computational Models of Development , 2001 .

[50]  Pierre-Yves Oudeyer,et al.  Intrinsic Motivation Systems for Autonomous Mental Development , 2007, IEEE Transactions on Evolutionary Computation.

[51]  G. Baldassarre,et al.  Evolving internal reinforcers for an intrinsically motivated reinforcement-learning robot , 2007, 2007 IEEE 6th International Conference on Development and Learning.

[52]  Charles Lee Isbell,et al.  Schema Learning: Experience-Based Construction of Predictive Action Models , 2004, NIPS.

[53]  Ronald C. Arkin,et al.  Robot tool behavior: a developmental approach to autonomous tool use , 2007 .

[54]  Filipo Studzinski Perotto,et al.  Learning regularities with a constructivist agent , 2006, AAMAS '06.

[55]  Paul R. Cohen,et al.  Concepts From Time Series , 1998, AAAI/IAAI.

[56]  Jefferson Provost and Benjamin J. Kuipers and Risto Miikkulainen.  Self-Organizing Distinctive State Abstraction Using Options , 2007 .

[57]  David J. Stracuzzi,et al.  A Statistical Approach to Incremental Induction of First-Order Hierarchical Knowledge Bases , 2008, ILP.

[58]  Clayton T. Morrison,et al.  An Image Schema Language , 2006 .

[59]  Gary L. Drescher,et al.  Made-up minds - a constructivist approach to artificial intelligence , 1991 .

[60]  Paul R. Cohen,et al.  A Method for Clustering the Experiences of a Mobile Robot that Accords with Human Judgments , 2000, AAAI/IAAI.

[61]  Paul R. Cohen,et al.  Neo: learning conceptual knowledge by sensorimotor interaction with an environment , 1997, AGENTS '97.

[62]  G. Lakoff,et al.  Metaphors We Live By , 1980 .

[63]  Georgi Stojanov,et al.  Interactivist approach to representation in epigenetic agents , 2003 .

[64]  Andrew G. Barto,et al.  Autonomous discovery of temporal abstractions from interaction with an environment , 2002 .

[65]  Paul R. Cohen,et al.  Continuous Categories For a Mobile Robot , 1999, AAAI/IAAI.

[66]  R. Brooks,et al.  Petitagé: A Case Study in Developmental Robotics , 2001 .

[67]  Sridhar Mahadevan,et al.  Hierarchical Memory-Based Reinforcement Learning , 2000, NIPS.

[68]  Paul R. Cohen,et al.  Bayesian Clustering by Dynamics Contents 1 Introduction 1 2 Clustering Markov Chains 2 , 2022 .

[69]  Paul R. Cohen,et al.  Abstracting from Robot Sensor Data using Hidden Markov Models , 1999, ICML.

[70]  Risto Miikkulainen,et al.  Developing navigation behavior through self-organizing distinctive-state abstraction , 2006, Connect. Sci..

[71]  Andrew G. Barto,et al.  Building Portable Options: Skill Transfer in Reinforcement Learning , 2007, IJCAI.

[72]  Risto Miikkulainen,et al.  The constructivist learning architecture: a model of cognitive development for robust autonomous robots , 2004 .

[73]  Nuttapong Chentanez,et al.  Intrinsically Motivated Reinforcement Learning , 2004, NIPS.

[74]  V. Lemaire,et al.  Active Learning using Adaptive Curiosity , 2006 .

[75]  R. A. Brooks,et al.  Intelligence without Representation , 1991, Artif. Intell..

[76]  J. Mandler.  How to build a baby: II. Conceptual primitives. , 1992, Psychological review.