Self-Organizing Distinctive State Abstraction Using Options

Abstract

An important problem in developmental robotics is the automatic learning of motor rou- tines or behaviors without human guidance. This paper presents Self-Organizing Distinctive-State Abstraction (SODA), a method by which a robot can learn a set of sensory features and reusable motor routines from raw sensorimotor experi- ence. Experiments show that the learned versions of the motor routines outperform hard-coded alternatives, and that robots using the learned routines can learn tasks much more quickly than when using primitive actions. The features and motor routines are learned autonomously, and reflect only the environment and the agent's sensorimotor capabilities, without external direction.