Learning Composable Models of Parameterized Skills

Leslie Kaelbling1, Tomas Lozano-Perez1

  • 1MIT



Regular Papers


11:30 - 12:45 | Tue 30 May | Room 4611/4612 | TUB6

Learning and Adaptive Systems 2

Full Text


There has been a great deal of work on learning new robot skills, but very little consideration of how these newly acquired skills can be integrated into an overall intelligent system. A key aspect of such a system is compositionality: newly learned abilities have to be characterized in a form that will allow them to be flexibly combined with existing abilities, affording a (good!) combinatorial explosion in the robotÂ’s abilities. In this paper, we focus on learning models of the preconditions and effects of new primitive actions, in a form that allows those actions to be combined with existing abilities by a generative planning and execution system.

Additional Information

No information added