Show simple item record

dc.contributor.authorArkin, Ronald C.
dc.contributor.authorMartinson, Eric
dc.date.accessioned2008-05-07T19:19:15Z
dc.date.available2008-05-07T19:19:15Z
dc.date.issued2003
dc.identifier.urihttp://hdl.handle.net/1853/21345
dc.description.abstractWe present an approach that uses Q-learning on individual robotic agents, for coordinating a mission-tasked team of robots in a complex scenario. To reduce the size of the state space, actions are grouped into sets of related behaviors called roles and represented as behavioral assemblages. A role is a Finite State Automata such as Forager, where the behaviors and their sequencing for finding objects, collecting them, and returning them are already encoded and do not have to be relearned. Each robot starts out with the same set of possible roles to play, the same perceptual hardware for coordination, and no contact other than perception regarding other members of the team. Over the course of training, a team of Q-learning robots will converge to solutions that best the performance of a well-designed handcrafted homogeneous team.en_US
dc.language.isoen_USen_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectMulti-robot systemsen_US
dc.subjectQ-learningen_US
dc.subjectRole-switchingen_US
dc.titleLearning to Role-Switch in Multi-Robot Systemsen_US
dc.typePaperen_US
dc.contributor.corporatenameGeorgia Institute of Technology. College of Computing
dc.contributor.corporatenameGeorgia Institute of Technology. Mobile Robot Laboratory


Files in this item

Thumbnail

This item appears in the following Collection(s)

  • Mobile Robot Laboratory [187]
    Papers, pre/post-prints, and presentations by faculty and students in the Georgia Tech Mobile Robot Laboratory.
  • Mobile Robot Laboratory Publications [187]
    Papers, pre/post-prints, and presentations by faculty and students in the Georgia Tech Mobile Robot Laboratory.

Show simple item record