Title:
Learning Roles: Behavioral Diversity in Robot Teams

dc.contributor.author Balch, Tucker en_US
dc.date.accessioned 2005-06-17T17:51:21Z
dc.date.available 2005-06-17T17:51:21Z
dc.date.issued 1997 en_US
dc.description.abstract This paper describes research investigating behavioral specialization in learning robot teams. Each agent is provided a common set of skills (motor schema-based behavioral assemblages) from which it builds a task-achieving strategy using reinforcement learning. The agents learn individually to activate particular behavioral assemblages given their current situation and a reward signal. The experiments, conducted in robot soccer simulations, evaluate the agents in terms of performance, policy convergence, and behavioral diversity. The results show that in many cases, robots will automatically diversify by choosing heterogeneous behaviors. The degree of diversification and the performance of the team depend on the reward structure. When the entire team is jointly rewarded or penalized (global reinforcement), teams tend towards heterogeneous behavior. When agents are provided feedback individually (local reinforcement), they converge to identical policies. en_US
dc.format.extent 201228 bytes
dc.format.mimetype application/pdf
dc.identifier.uri http://hdl.handle.net/1853/6647
dc.language.iso en_US
dc.publisher Georgia Institute of Technology en_US
dc.relation.ispartofseries CC Technical Report; GIT-CC-97-12 en_US
dc.subject Machine learning
dc.subject Multi-robot teams
dc.subject Reinforcement learning
dc.subject Global reinforcement
dc.title Learning Roles: Behavioral Diversity in Robot Teams en_US
dc.type Text
dc.type.genre Technical Report
dspace.entity.type Publication
local.contributor.corporatename College of Computing
local.relation.ispartofseries College of Computing Technical Report Series
relation.isOrgUnitOfPublication c8892b3c-8db6-4b7b-a33a-1b67f7db2021
relation.isSeriesOfPublication 35c9e8fc-dd67-4201-b1d5-016381ef65b8
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
GIT-CC-97-12.pdf
Size:
196.51 KB
Format:
Adobe Portable Document Format
Description: