Hierarchical Behavioral Repertoires with Unsupervised Descriptors

Abstract

Enabling artificial agents to automatically learn complex, versatile and high-performing behaviors is a long-lasting challenge. This paper presents a step in this direction with hierarchical behavioral repertoires that stack several behavioral repertoires to generate sophisticated behaviors. Each repertoire of this architecture uses the lower repertoires to create complex behaviors as sequences of simpler ones, while only the lowest repertoire directly controls the agent's movements. This paper also introduces a novel approach to automatically define behavioral descriptors thanks to an unsupervised neural network that organizes the produced high-level behaviors. The experiments show that the proposed architecture enables a robot to learn how to draw digits in an unsupervised manner after having learned to draw lines and arcs. Compared to traditional behavioral repertoires, the proposed architecture reduces the dimensionality of the optimization problems by orders of magnitude and provides behaviors with a twice better fitness. More importantly, it enables the transfer of knowledge between robots: a hierarchical repertoire evolved for a robotic arm to draw digits can be transferred to a humanoid robot by simply changing the lowest layer of the hierarchy. This enables the humanoid to draw digits although it has never been trained for this task.

arXiv commentGECCO 2018

References in corpus (5)

• Robots that can adapt like animals
• Illuminating search spaces by mapping elites
• Reset-free Trial-and-Error Learning for Robot Damage Recovery
• MAGAN: Margin Adaptation for Generative Adversarial Networks
• Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted Illumination

Cited by in corpus (13)

• Evolving embodied intelligence from materials to machines
• AlphaStar: An Evolutionary Computation Perspective
• Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors
• Fast and stable MAP-Elites in noisy domains using deep grids
• Empirical analysis of PGA-MAP-Elites for Neuroevolution in Uncertain Domains
• Hierarchical Quality-Diversity for Online Damage Recovery
• Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains
• BR-NS: an Archive-less Approach to Novelty Search
• The Quality-Diversity Transformer: Generating Behavior-Conditioned Trajectories with Decision Transformers
• Enhancing MAP-Elites with Multiple Parallel Evolution Strategies
• Generation Drawing/Grinding Trajectoy Based on Hierarchical CVAE
• On the use of feature-maps and parameter control for improved quality-diversity meta-evolution
• Learning in Sparse Rewards settings through Quality-Diversity algorithms