Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learner

By Sao Mai Nguyen, Pierre-Yves Oudeyer. 2012

54 citations recorded by the source corpus.

We present an active learning architecture that allows a robot to actively learn which data collection strategy is most efficient for acquiring motor skills to achieve multiple outcomes, and generalise over its experience to achieve new outcomes. The robot explores its environment both via interactive learning and goal-babbling. It learns at the same time when, who and what to actively imitate from several available teachers, and learns when not to use social guidance but use active goal-oriented self-exploration. This is formalised in the framework of life-long strategic learning.The proposed architecture, called Socially Guided Intrinsic Motivation with Active Choice of Teacher and Strategy (SGIM-ACTS), relies on hierarchical active decisions of what and how to learn driven by empirical evaluation of learning progress for each learning strategy. We illustrate with an experiment where a simulated robot learns to control its arm for realising two kinds of different outcomes. It has to choose actively and hierarchically at each learning episode: 1) what to learn: which outcome is most interesting to select as a goal to focus on for goal-directed exploration; 2) how to learn: which data collection strategy to use among self-exploration, mimicry and emulation; 3) once he has decided when and what to imitate by choosing mimicry or emulation, then he has to choose who to imitate, from a set of different teachers. We show that SGIM-ACTS learns significantly more effciently than using single learning strategies, and coherently selects the best strategy with respect to the chosen outcome, taking advantage of the available teachers (with different levels of skills).

Subfields: Artificial Intelligence, Control and Systems Engineering, Developmental and Educational Psychology, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

In Developmental and Educational Psychology

In Meta & Continual Learning

Citations in the corpus

What can the brain teach us about building artificial intelligence? (2016, background): “ curiosity-driven selection of parameterized problems (Baranes and Oudeyer, 2013), of learning strategies (Lopes and Oudeyer, 2012), and combinations between intrinsic motivation and social learning (Nguyen and Oudeyer, 2013), have not yet been integrated with deep learning. Embodied self-organizati”
How Evolution May Work Through Curiosity-Driven Developmental Process (2016, background): “Other robotic models have explored how social guidance can be leveraged by an intrinsically motivated active learner and dynamically interact with curiosity to structure developmental trajectories (Thomaz and Breazeal, 2008; Nguyen and Oudeyer, 2013).”
Self-organization of early vocal development in infants and machines: the role of intrinsic motivation (2014, methodology): “In a second series of experiments (section 3.2), we extend the previous model by integrating the previous learning algorithm in the SGIM-ACTS architecture, which has been proposed in Nguyen and Oudeyer (2012).”
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning (2018, unknown): “MACOB maintains a population of solutions, one for each goal ( modular goal-experts approach), see Nguyen & Oudeyer (2012) for a similar approach.”
Socially guided intrinsic motivation for robot learning of motor skills (2013, methodology): “This choice of taking only 4 samples of the movement trajectory is arbitrarily, and other parametrisations have been also used in other studies (Nguyen and Oudeyer 2012b,a).”