Action chaining by a developmental robot with a value system

摘要

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.