C. Han Yong and R. Miikkulainen, Cooperative Coevolution of Multi-Agent Systems. Technical Report AI01-287, Department of Computer Sciences, University of Texas at Austin,1999 Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Concurrent Layered Learning - Whiteson, Stone (2003) (3 citations) (Correct)
....perform di erent roles but are evaluated in a common domain. Coevolution can be competitive [7, 13] in which case these roles are adversarial and one component s gain is another s loss. Coevolution can also be cooperative [12] as when the various components share tness scores. Multi Agent ESP [22] is an extension of ESP that allows multiple components to coevolve cooperatively. In this system, each component is evolved with a separate, concurrent run of ESP. For each tness evaluation, Multi Agent ESP forms a network from each ESP and then evaluates these networks together in the task, all ....
....run of ESP. For each tness evaluation, Multi Agent ESP forms a network from each ESP and then evaluates these networks together in the task, all of which receive the same score when the evaluation completes. MultiAgent ESP has been successfully used to master multi agent predator prey tasks [22]. In concurrent layered learning, before training in L i 1 begins, we take the best network from L i and use it to seed a new population. This new population continues to learn along with a separate population learning L i 1 . Hence, we evolve the two layers cooperatively using the same method as ....
C. H. Yong and R. Miikkulainen. Cooperative coevolution of multi-agent systems. Technical Report AI01-287, The University of Texas at Austin Department of Computer Sciences, 2001.
Evolving Keepaway Soccer Players through Task.. - Whiteson, Kohl.. (2003) Self-citation (Miikkulainen) (Correct)
....loss. Coevolution can also be cooperative [9] as when the various components share tness scores. In our case, we use an extension of ESP designed to coevolve several cooperating components. This method, called Multi Agent ESP, has been successfully used to master multi agent predator prey tasks [18]. In Multi Agent ESP, each component is evolved with a separate, concurrent run of ESP. During a tness evaluation, networks are formed in each ESP and evaluated together in the task. All the networks that participate in the evaluation receive the same score. Therefore, the component ESPs coevolve ....
C. H. Yong and R. Miikkulainen. Cooperative coevolution of multi-agent systems. Technical Report AI01-287, The University of Texas at Austin Department of Computer Sciences, 2001.
Neuro-evolved Agent-based Cooperative Controller for a.. - Tellez, Angulo (2004) (Correct)
No context found.
C. Han Yong and R. Miikkulainen, Cooperative Coevolution of Multi-Agent Systems. Technical Report AI01-287, Department of Computer Sciences, University of Texas at Austin,1999
Evolving Neural Networks for the Capture Game - Konidaris, Shell, Oren (2002) (Correct)
No context found.
C.H. Yong and R. Miikkulainen. Cooperative coevolution of multi-agent systems. Technical Report AI01-287, The University of Texas at Austin, 2001.
When Evolving Populations is Better than Coevolving Individuals.. - Miconi (2003) (Correct)
No context found.
C. Yong and R. Mikkulainen. Cooperative coevolution of multi-agent systems. Technical Report AI01-287, University of Texas at Austin, 2001. 6
Evolving Neural Networks for the Capture Game - Konidaris, Shell, Oren (2002) (Correct)
No context found.
C.H. Yong and R. Miikkulainen. Cooperative coevolution of multi-agent systems. Technical Report AI01-287, The University of Texas at Austin, 2001. 10
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC