This paper shows the computational bene"ts of a game theoretic approach to optimization of high dimensional control problems. A dynamic noncooperative game framework is adopted to partition the control space and to search the optimum as the equilibrium of a k-person dynamic game played by k-parallel
β¦ LIBER β¦
Learning equilibrium as a generalization of learning to optimize
β Scribed by Dov Monderer; Moshe Tennenholtz
- Publisher
- Elsevier Science
- Year
- 2007
- Tongue
- English
- Weight
- 107 KB
- Volume
- 171
- Category
- Article
- ISSN
- 0004-3702
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
Learning the optimum as a Nash equilibri
β
SΓΌheyla ΓzyΔ±ldΔ±rΔ±m; Nedim M. Alemdar
π
Article
π
2000
π
Elsevier Science
π
English
β 232 KB
A generalization of the learning curve
β
James R. Dorroh; Thomas R. Gulledge Jr.; Norman Keith Womer
π
Article
π
1986
π
Elsevier Science
π
English
β 705 KB
A hierarchy machine: Learning to optimiz
β
Martin Pelikan; David E. Goldberg
π
Article
π
2003
π
John Wiley and Sons
π
English
β 222 KB
A methodology to learn designing optimal
β
Gloria Galan-Marin; F. Javier Alonso-Sanchez; Jose M. Del Castillo-Granados
π
Article
π
2009
π
John Wiley and Sons
π
English
β 121 KB
π 1 views
## Abstract The study of fourβbar linkages to trace a desired path is an important part of teaching in mechanical design. When the number of precision points exceeds a certain number, most recent approaches utilize intelligent optimization methods based on too complex computer science theories to b
Ξ΅-Optimality of a general class of learn
β
M.R. Meybodi; S. Lakshmivarahan
π
Article
π
1982
π
Elsevier Science
π
English
β 831 KB
Convergence of reinforcement learning to
β
Eric Darmon; Roger Waldeck
π
Article
π
2005
π
Elsevier Science
π
English
β 240 KB