Modular active curiosity-driven discovery of tool use
Authors:
- 1 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3965-3972
Abstract
This article studies algorithms used by a learner to explore high-dimensional structured sensorimotor spaces such as in tool use discovery. In particular, we consider goal babbling architectures that were designed to explore and learn solutions to fields of sensorimotor problems, i.e. to acquire inverse models mapping a space of parameterized sensorimotor problems/effects to a corresponding space of parameterized motor primitives. However, so far these architectures have not been used in high-dimensional spaces of effects. Here, we show the limits of existing goal babbling architectures for efficient exploration in such spaces, and introduce a novel exploration architecture called Model Babbling (MB). MB exploits efficiently a modular representation of the space of parameterized problems/effects. We also study an active version of Model Babbling (the MACOB architecture). These architectures are compared in a simulated experimental setup with an arm that can discover and learn how to move objects using two tools with different properties, embedding structured high-dimensional continuous motor and sensory spaces.Keywords
This publication has 25 references indexed in Scilit:
- Staged Development of Robot Skills: Behavior Formation, Affordance Learning and Imitation with MotioneseIEEE Transactions on Autonomous Mental Development, 2015
- Self-organization of early vocal development in infants and machines: the role of intrinsic motivationFrontiers in Psychology, 2014
- Socially guided intrinsic motivation for robot learning of motor skillsAutonomous Robots, 2013
- Dynamical Movement Primitives: Learning Attractor Models for Motor BehaviorsNeural Computation, 2013
- Robot Skill Learning: From Reinforcement Learning to Evolution StrategiesPaladyn, 2013
- Active learning of inverse models with intrinsically motivated goal exploration in robotsRobotics and Autonomous Systems, 2013
- Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation LearnerPaladyn, 2012
- Behavior-Grounded Representation of Tool Affordances2006
- A Limited Memory Algorithm for Bound Constrained OptimizationSIAM Journal on Scientific Computing, 1995
- Locally Weighted Regression: An Approach to Regression Analysis by Local FittingJournal of the American Statistical Association, 1988