Learning Reliable Manipulation Strategies Without Initial Physical Models

Abstract

We describe a robot, possessing limited sensory and effectory capabilties but no initial model of the effects of its actions on the world, that acquires such a model through exploration, practice, and observation. By acquiring an increasingly correct model of its actions, it generates increasingly successful plans to achieve its goals. In an apparently non-deterministic world, achieving reliability requires the identification of reliable actions and a preference for using such actions. Furthermore, by selecting its training carefully, the robot can significantly improve its learning rate.