DSpace Repository

Interaction and Intelligent Behavior

Show simple item record

dc.creator Mataric, Maja J.
dc.date 2004-11-19T17:19:50Z
dc.date 2004-11-19T17:19:50Z
dc.date 1994-08-01
dc.date.accessioned 2013-10-09T02:49:16Z
dc.date.available 2013-10-09T02:49:16Z
dc.date.issued 2013-10-09
dc.identifier AITR-1495
dc.identifier http://hdl.handle.net/1721.1/7343
dc.identifier.uri http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description We introduce basic behaviors as primitives for control and learning in situated, embodied agents interacting in complex domains. We propose methods for selecting, formally specifying, algorithmically implementing, empirically evaluating, and combining behaviors from a basic set. We also introduce a general methodology for automatically constructing higher--level behaviors by learning to select from this set. Based on a formulation of reinforcement learning using conditions, behaviors, and shaped reinforcement, out approach makes behavior selection learnable in noisy, uncertain environments with stochastic dynamics. All described ideas are validated with groups of up to 20 mobile robots performing safe--wandering, following, aggregation, dispersion, homing, flocking, foraging, and learning to forage.
dc.format 177 p.
dc.format 15039745 bytes
dc.format 1008036 bytes
dc.format application/postscript
dc.format application/pdf
dc.language en_US
dc.relation AITR-1495
dc.subject group behavior
dc.subject learning
dc.subject multi-agent systems
dc.subject situated agents
dc.subject behavior-based control
dc.subject collective behavior
dc.title Interaction and Intelligent Behavior

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account