Socially guided intrinsic motivation for robot learning of motor skills

Authors:
Sao Mai Nguyen;Pierre-Yves Oudeyer
Affiliations:
Flowers Team, INRIA and ENSTA ParisTech, Paris, France;Flowers Team, INRIA and ENSTA ParisTech, Paris, France
Venue:
Autonomous Robots
Year:
2014

Citing 31
Cited 0

Principles of multivariate analysis: a user's perspective

Principles of multivariate analysis: a user's perspective
A teaching method for reinforcement learning

ML92 Proceedings of the ninth international workshop on Machine learning
On the convergence of interior-reflective Newton methods for nonlinear minimization subject to bounds

Mathematical Programming: Series A and B
Integrated learning for interactive synthetic characters

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Convergence Properties of the Nelder--Mead Simplex Method in Low Dimensions

SIAM Journal on Optimization
Toward Optimal Active Learning through Sampling Estimation of Error Reduction

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Imitation in animals and artifacts

Imitation in animals and artifacts
Three sources of information in social learning

Imitation in animals and artifacts
Natural methods for robot task learning: instructive demonstrations, generalization and practice

AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Apprenticeship learning via inverse reinforcement learning

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Socially guided machine learning

Socially guided machine learning
2008 Special Issue: Reinforcement learning of motor skills with policy gradients

Neural Networks
Experiments in socially guided exploration: lessons learned in building robots that learn with and without human teachers

Connection Science - Social Learning in Embodied Agents
A survey of robot learning from demonstration

Robotics and Autonomous Systems
Interactive policy learning through confidence-based autonomy

Journal of Artificial Intelligence Research
Active learning with statistical models

Journal of Artificial Intelligence Research
A Computational Model of Social-Learning Mechanisms

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Robot Programming by Demonstration

Robot Programming by Demonstration
2010 Special Issue: Communication and knowledge sharing in human-robot interaction and learning from demonstration

Neural Networks
Teacher feedback to scaffold and refine demonstrated motion primitives on a mobile robot

Robotics and Autonomous Systems
Policy search for motor primitives in robotics

Machine Learning
Trajectories and keyframes for kinesthetic teaching: a human-robot interaction perspective

HRI '12 Proceedings of the seventh annual ACM/IEEE international conference on Human-Robot Interaction
Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990–2010)

IEEE Transactions on Autonomous Mental Development
Goal Babbling Permits Direct Learning of Inverse Kinematics

IEEE Transactions on Autonomous Mental Development
Designing Interactions for Robot Active Learners

IEEE Transactions on Autonomous Mental Development
Guest Editorial Active Learning and Intrinsically Motivated Exploration in Robots: Advances and Challenges

IEEE Transactions on Autonomous Mental Development
Intrinsic Motivation Systems for Autonomous Mental Development

IEEE Transactions on Evolutionary Computation
On Learning, Representing, and Generalizing a Task in a Humanoid Robot

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Active learning of inverse models with intrinsically motivated goal exploration in robots

Robotics and Autonomous Systems
Learning the combinatorial structure of demonstrated behaviors with inverse feedback control

HBU'12 Proceedings of the Third international conference on Human Behavior Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a technical approach to robot learning of motor skills which combines active intrinsically motivated learning with imitation learning. Our algorithmic architecture, called SGIM-D, allows efficient learning of high-dimensional continuous sensorimotor inverse models in robots, and in particular learns distributions of parameterised motor policies that solve a corresponding distribution of parameterised goals/tasks. This is made possible by the technical integration of imitation learning techniques within an algorithm for learning inverse models that relies on active goal babbling. After reviewing social learning and intrinsic motivation approaches to action learning, we describe the general framework of our algorithm, before detailing its architecture. In an experiment where a robot arm has to learn to use a flexible fishing line, we illustrate that SGIM-D efficiently combines the advantages of social learning and intrinsic motivation and benefits from human demonstration properties to learn how to produce varied outcomes in the environment, while developing more precise control policies in large spaces.