Show simple item record

dc.contributor.authorMataric, Maja J.en_US
dc.date.accessioned2004-11-19T17:19:50Z
dc.date.available2004-11-19T17:19:50Z
dc.date.issued1994-08-01en_US
dc.identifier.otherAITR-1495en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/7343
dc.description.abstractWe 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.en_US
dc.format.extent177 p.en_US
dc.format.extent15039745 bytes
dc.format.extent1008036 bytes
dc.format.mimetypeapplication/postscript
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.relation.ispartofseriesAITR-1495en_US
dc.subjectgroup behavioren_US
dc.subjectlearningen_US
dc.subjectmulti-agent systemsen_US
dc.subjectsituated agentsen_US
dc.subjectbehavior-based controlen_US
dc.subjectcollective behavioren_US
dc.titleInteraction and Intelligent Behavioren_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record