(Created page with " == Abstract == Multiagent systems have had a powerful impact on the real world. Many of the systems it studies air traffic, satellite coordination, rover exploration are inh...") |
|||
| (One intermediate revision by the same user not shown) | |||
| Line 3: | Line 3: | ||
Multiagent systems have had a powerful impact on the real world. Many of the systems it studies air traffic, satellite coordination, rover exploration are inherently multi-objective, but they are often treated as single-objective problems within the research. A very important concept within multiagent systems is that of credit assignment: clearly quantifying an individual agent's impact on the overall system performance. In this work we extend the concept of credit assignment into multi-objective problems, broadening the traditional multiagent learning framework to account for multiple objectives. We show in two domains that by leveraging established credit assignment principles in a multi-objective setting, we can improve performance by i increasing learning speed by up to 10x ii reducing sensitivity to unmodeled disturbances by up to 98.4% and iii producing solutions that dominate all solutions discovered by a traditional team-based credit assignment schema. Our results suggest that in a multiagent multi-objective problem, proper credit assignment is as important to performance as the choice of multi-objective algorithm. | Multiagent systems have had a powerful impact on the real world. Many of the systems it studies air traffic, satellite coordination, rover exploration are inherently multi-objective, but they are often treated as single-objective problems within the research. A very important concept within multiagent systems is that of credit assignment: clearly quantifying an individual agent's impact on the overall system performance. In this work we extend the concept of credit assignment into multi-objective problems, broadening the traditional multiagent learning framework to account for multiple objectives. We show in two domains that by leveraging established credit assignment principles in a multi-objective setting, we can improve performance by i increasing learning speed by up to 10x ii reducing sensitivity to unmodeled disturbances by up to 98.4% and iii producing solutions that dominate all solutions discovered by a traditional team-based credit assignment schema. Our results suggest that in a multiagent multi-objective problem, proper credit assignment is as important to performance as the choice of multi-objective algorithm. | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| Line 15: | Line 10: | ||
* [http://web.engr.oregonstate.edu/%7Ektumer/publications/files/tumer-yliniemi_moma-seal14.pdf http://web.engr.oregonstate.edu/%7Ektumer/publications/files/tumer-yliniemi_moma-seal14.pdf] | * [http://web.engr.oregonstate.edu/%7Ektumer/publications/files/tumer-yliniemi_moma-seal14.pdf http://web.engr.oregonstate.edu/%7Ektumer/publications/files/tumer-yliniemi_moma-seal14.pdf] | ||
| + | |||
| + | * [http://link.springer.com/content/pdf/10.1007/978-3-319-13563-2_35 http://link.springer.com/content/pdf/10.1007/978-3-319-13563-2_35], | ||
| + | : [http://dx.doi.org/10.1007/978-3-319-13563-2_35 http://dx.doi.org/10.1007/978-3-319-13563-2_35] | ||
| + | |||
| + | * [http://web.engr.oregonstate.edu/~ktumer/publications/files/tumer-yliniemi_moma-seal14.pdf http://web.engr.oregonstate.edu/~ktumer/publications/files/tumer-yliniemi_moma-seal14.pdf], | ||
| + | : [https://link.springer.com/chapter/10.1007/978-3-319-13563-2_35 https://link.springer.com/chapter/10.1007/978-3-319-13563-2_35], | ||
| + | : [https://www.scipedia.com/public/Yliniemi_Tumer_2014a https://www.scipedia.com/public/Yliniemi_Tumer_2014a], | ||
| + | : [https://dblp.uni-trier.de/db/conf/seal/seal2014.html#YliniemiT14a https://dblp.uni-trier.de/db/conf/seal/seal2014.html#YliniemiT14a], | ||
| + | : [https://rd.springer.com/chapter/10.1007/978-3-319-13563-2_35 https://rd.springer.com/chapter/10.1007/978-3-319-13563-2_35], | ||
| + | : [https://academic.microsoft.com/#/detail/285701945 https://academic.microsoft.com/#/detail/285701945] | ||
Latest revision as of 16:16, 21 January 2021
Abstract
Multiagent systems have had a powerful impact on the real world. Many of the systems it studies air traffic, satellite coordination, rover exploration are inherently multi-objective, but they are often treated as single-objective problems within the research. A very important concept within multiagent systems is that of credit assignment: clearly quantifying an individual agent's impact on the overall system performance. In this work we extend the concept of credit assignment into multi-objective problems, broadening the traditional multiagent learning framework to account for multiple objectives. We show in two domains that by leveraging established credit assignment principles in a multi-objective setting, we can improve performance by i increasing learning speed by up to 10x ii reducing sensitivity to unmodeled disturbances by up to 98.4% and iii producing solutions that dominate all solutions discovered by a traditional team-based credit assignment schema. Our results suggest that in a multiagent multi-objective problem, proper credit assignment is as important to performance as the choice of multi-objective algorithm.
Original document
The different versions of the original document can be found in:
Document information
Published on 01/01/2014
Volume 2014, 2014
DOI: 10.1007/978-3-319-13563-2_35
Licence: CC BY-NC-SA license
Share this document
Keywords
claim authorship
Are you one of the authors of this document?