November
1991
Learning Reliable Manipulation Strategies Without Initial Physical Models
Authors:
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.
copied = false, 2000);
">
@article{Christiansen-1991-15810,
author = {Alan D. Christiansen And Matthew T. Mason And Tom Mitchell},
title = {Learning Reliable Manipulation Strategies Without Initial Physical Models},
journal = {Proceedings of Robotics and Autonomous Systems},
year = {1991},
month = {November},
volume = {8},
number = {1},
pages = {7 - 18},
}
author = {Alan D. Christiansen And Matthew T. Mason And Tom Mitchell},
title = {Learning Reliable Manipulation Strategies Without Initial Physical Models},
journal = {Proceedings of Robotics and Autonomous Systems},
year = {1991},
month = {November},
volume = {8},
number = {1},
pages = {7 - 18},
}