Neuro-dynamic programming /
Neuro-dynamic programming, also known as reinforcement learning, is a recent methodology that can be used to solve very large and complex stochastic decision and control problems. It combines simulation, learning, neural networks or other approximation architectures, and the central ideas in dynamic...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Book |
| Language: | English |
| Published: |
Belmont, Mass. :
Athena Scientific,
[1996], ©1996
Belmont, Mass. : c1996 Belmont, Mass. : ©1996 |
| Series: | Athena Scientific series in optimization and neural computation
3 Optimization and neural computation series ; 3 Optimization and neural computation series Optimization and neural computation series ; 3 Optimization and neural computation series 3 Optimization and neural computation series |
| Subjects: |
Internet
Stanford University
| Call Number: |
QA76.87 .B477 1996 |
|---|
University of Chicago
| Call Number: |
QA76.87.B47 1996 |
|---|
Massachusetts Institute of Technology
| Call Number: |
QA76.87.B47 1996 |
|---|
Johns Hopkins University
| Call Number: |
QA76.87.B47 1996 |
|---|
Harvard University
| Call Number: |
QA76.87 .B47 1996 QA76.87 .B47 1996x |
|---|
Duke University
| Call Number: |
QA76.87 .B47 1996 |
|---|
Dartmouth College
| Call Number: |
QA76.87 .B477 1996 |
|---|
Cornell University
| Call Number: |
QA76.87 .B47x 1996 |
|---|
Princeton University
| Call Number: |
QA76.87 .B477 1996 |
|---|
Columbia University
| Call Number: |
QA76.87 .B47 1996g |
|---|
Brown University
| Call Number: |
QA76.87 .B47 1996 |
|---|