Interaction and Intelligent Behavior
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 introd...
Main Author: | |
---|---|
Language: | en_US |
Published: |
2004
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/7343 |
_version_ | 1811092952974360576 |
---|---|
author | Mataric, Maja J. |
author_facet | Mataric, Maja J. |
author_sort | Mataric, Maja J. |
collection | MIT |
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. |
first_indexed | 2024-09-23T15:37:06Z |
id | mit-1721.1/7343 |
institution | Massachusetts Institute of Technology |
language | en_US |
last_indexed | 2024-09-23T15:37:06Z |
publishDate | 2004 |
record_format | dspace |
spelling | mit-1721.1/73432019-04-12T08:34:40Z Interaction and Intelligent Behavior Mataric, Maja J. group behavior learning multi-agent systems situated agents behavior-based control collective behavior 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. 2004-11-19T17:19:50Z 2004-11-19T17:19:50Z 1994-08-01 AITR-1495 http://hdl.handle.net/1721.1/7343 en_US AITR-1495 177 p. 15039745 bytes 1008036 bytes application/postscript application/pdf application/postscript application/pdf |
spellingShingle | group behavior learning multi-agent systems situated agents behavior-based control collective behavior Mataric, Maja J. Interaction and Intelligent Behavior |
title | Interaction and Intelligent Behavior |
title_full | Interaction and Intelligent Behavior |
title_fullStr | Interaction and Intelligent Behavior |
title_full_unstemmed | Interaction and Intelligent Behavior |
title_short | Interaction and Intelligent Behavior |
title_sort | interaction and intelligent behavior |
topic | group behavior learning multi-agent systems situated agents behavior-based control collective behavior |
url | http://hdl.handle.net/1721.1/7343 |
work_keys_str_mv | AT mataricmajaj interactionandintelligentbehavior |