Abstract
A hypothesis regarding the development of imitation learning is presented that is rooted in intrinsic motivations. It is derived from a recently proposed form of intrinsically motivated learning (IML) for efficient coding in active perception, wherein an agent learns to perform actions with its sense organs to facilitate efficient encoding of the sensory data. To this end, actions of the sense organs that improve the encoding of the sensory data trigger an internally generated reinforcement signal. Here it is argued that the same IML mechanism might also support the development of imitation when general actions beyond those of the sense organs are considered: The learner first observes a tutor performing a behavior and learns a model of the the behavior's sensory consequences. The learner then acts itself and receives an internally generated reinforcement signal reflecting how well the sensory consequences of its own behavior are encoded by the sensory model. Actions that are more similar to those of the tutor will lead to sensory signals that are easier to encode and produce a higher reinforcement signal. Through this, the learner's behavior is progressively tuned to make the sensory consequences of its actions match the learned sensory model. I discuss this mechanism in the context of human language acquisition and bird song learning where similar ideas have been proposed. The suggested mechanism also offers an account for the development of mirror neurons and makes a number of predictions. Overall, it establishes a connection between principles of efficient coding, intrinsic motivations and imitation.
Highlights
Imitation is a powerful form of learning where an agent acquires a skill from observing the skill being performed by a second agent
A corresponding account for the development of mirror neurons was presented. It combines previous proposals based on associative Hebbian learning and instrumental or reinforcement learning in the framework of intrinsically motivated learning (IML)
Once established through www.frontiersin.org either of these mechanisms, it is easy to see how mirror neurons could contribute to various forms of imitation including automatic imitation (Heyes, 2010) and vocal mimicry
Summary
Imitation is a powerful form of learning where an agent acquires a skill from observing the skill being performed by a second agent. Recent learning accounts considering possible underlying neurobiological mechanisms have rested on associative (Hebbian) learning (Heyes and Ray, 2000; Keysers and Perrett, 2004) or reinforcement learning (Triesch et al, 2007) These are sufficient for the development of a simple form of imitation called response facilitation, where the agent learns to map the observation of a behavior performed by a second agent onto an already existing motor representation for performing the same behavior. I discuss how a recently proposed intrinsically motivated learning (IML) mechanism for efficient coding in active perception might be generalized for this form of imitation learning This suggests that principles of efficient sensory coding may be a foundation for song learning in birds and speech acquisition in humans. The observation of a certain disparity at the center of gaze is found to afford a certain vergence command that will lead to an improved representation of this input
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
