Abstract | ||
---|---|---|
This paper proposes a solution methodology for a missile defense problem involving the sequential allocation of defensive resources over a series of engagements. The problem is cast as a dynamic programming/Markovian decision problem, which is computationally intractable by exact methods because of its large number of states and its complex modeling issues. We employed a neuro-dynamic programming framework, whereby the cost-to-go function is approximated using neural network architectures that are trained on simulated data. We report on the performance obtained using several different training methods, and we compare this performance with the optimal approach |
Year | DOI | Venue |
---|---|---|
2000 | 10.1109/3468.823480 | IEEE Transactions on Systems, Man, and Cybernetics, Part A |
Keywords | Field | DocType |
functional programming,learning artificial intelligence,neural nets,computational modeling,missile defense,operations research,indexing terms,computer architecture,decision problem,dynamic programming,resource allocation,resource management,neural network,reinforcement learning,neural networks | Dynamic programming,Mathematical optimization,Decision problem,Functional programming,Missile defense,Computer science,Resource allocation,Artificial intelligence,Artificial neural network,Software framework,Machine learning,Reinforcement learning | Journal |
Volume | Issue | ISSN |
30 | 1 | 1083-4427 |
Citations | PageRank | References |
28 | 1.62 | 5 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
D. P. Bertsekas | 1 | 215 | 36.05 |
M. L. Homer | 2 | 28 | 1.62 |
D. A. Logan | 3 | 28 | 1.62 |
Stephen D. Patek | 4 | 131 | 17.32 |
Nils R. Sandell | 5 | 28 | 1.62 |