Interaction and Intelligent Behavior

Title: en_US Interaction and Intelligent Behavior
Creator: en_US Mataric, Maja J.
Date: 2004-11-19T17:19:50Z
Date Available: 2004-11-19T17:19:50Z
Date Issued: en_US 1994-08-01
Identifier: en_US AITR-1495
uri: http://hdl.handle.net/1721.1/7343
Abstract: en_US 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.
Extent: en_US 177 p.; 15039745 bytes; 1008036 bytes
Format: application/postscript; application/pdf
Language: en_US
Relation: en_US AITR-1495
Subject: en_US group behavior; en_US learning; en_US multi-agent systems; en_US situated agents; en_US behavior-based control; en_US collective behavior