Action chaining by a developmental robot with a value system

A developmental cognitive learning architecture with a value system is proposed for an artificial agent to learn composite behaviors upon the acquisition of basic ones. This work is motivated by researches on classical conditioning in animal learning areas. Compared to former works, the proposed architecture enables an agent to conduct learning in unknown environments through online realtime experiences. All possible perceptions and actions, including even the actual number of classes, are not available until the programming is finished and the robot starts to learn in the real world. Experiments with our SAIL (Self-organizing Autonomous Incremental Learner) robot are reported to show how a trainer instructed (or shaped) the behaviors of the agent through verbal commands.

[1]  M. Domjan.  The principles of learning and behavior , 1982 .

[2]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[3]  David S. Touretzky,et al.  Shaping robot behavior using principles from instrumental conditioning , 1997, Robotics Auton. Syst..

[4]  David S. Touretzky,et al.  Operant Conditioning in Skinnerbots , 1997, Adapt. Behav..

[5]  Christian Balkenius,et al.  Computational models of classical conditioning: a comparative study , 1998 .

[6]  Alex Pentland,et al.  Learning audio-visual associations using mutual information , 1999, Proceedings Integration of Speech and Image Understanding.

[7]  Olaf Sporns,et al.  Plasticity in Value Systems and its Role in Adaptive Behavior , 2000, Adapt. Behav..

[8]  Juyang Weng,et al.  Developmental Humanoids: Humanoids that Develop Skills Automatically , 2000 .

[9]  J. Weng,et al.  Grounded Auditory Development by a Developmental Robot 1 , 2001 .

[10]  Ying Wu,et al.  Robot speech learning via entropy guided LVQ and memory association , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[11]  Juyang Weng,et al.  Chained action learning through real-time interactions , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[12]  Peter Dayan,et al.  Q-learning , 1992, Machine Learning.