Learning from Observation Using Primitives

DMCA

Learning from Observation Using Primitives (2004)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Darrin C. Bentivegna , Christopher G. Atkeson

Citations:

70 - 5 self

BibTeX

@TECHREPORT{Bentivegna04learningfrom,
    author = {Darrin C. Bentivegna and Christopher G. Atkeson},
    title = {Learning from Observation Using Primitives},
    institution = {},
    year = {2004}
}

OpenURL

Abstract

This paper describes the use of task primitives in robot learning from observation. A framework has been developed that uses observed data to initially learn a task and then the agent goes on to increase its performance through repeated task performance (learning from practice). Data that is collected while a human performs a task is parsed into small parts of the task called primitives. Modules are created for each primitive that encode the movements required during the performance of the primitive, and when and where the primitives are performed. The feasibility of this method is currently being tested with agents that learn to play a virtual and an actual air hockey game. 1

Keyphrases

observation using primitive task performance task primitive small part actual air hockey game robot learning

DMCA