All Packages Class Hierarchy This Package Previous Next Index
Class sim.gradDesc.IDD
java.lang.Object
|
+----sim.Experiment
|
+----sim.gradDesc.GradDesc
|
+----sim.gradDesc.IDD
- public class IDD
- extends GradDesc
Incremental Delta Delta (reference "Multi-Agent Residual Advantage Learning With
General Function Approximation" on publication list at http://www-anw.cs.umass.edu/~mharmon).
This code is (c) 1997 Mance Harmon
<mharmon@acm.org>,
http://www-anw.cs.umass.edu/~mharmon
The source and object code may be redistributed freely.
If the code is modified, please state so in the comments.
- Version:
- 0.9, 22 July 97 This code will become 1.0 when autoparse is done.
- Author:
- Mance Harmon
-
alphas
- the learning rates, alpha = e^beta(i)
-
betas
- the beta matrix
-
errFun
- the error function to minimize
-
error
- a noisy estimate of the error being gradient descended on
-
logSmoothedError
- log base 10 of the smoothed error
-
pAlphas
- a pointer to alphas
-
pBetas
- a pointer to the betas
-
rndCopy
- a copy of the generator passed to evaluate().
-
smoothedError
- an exponentially smoothed estimate of the error
-
smoothingFactor
- the constant used to smooth the error (near 1 = long halflife)
-
theta
- the learning rate, a small positive number
-
time
- current time (time increments once per weight change
-
tolerance
- stop learning when smoothed error < tolerance
-
weightChange1
- the change in the weights at time t
-
weightChange2
- the change in the weights at time t+1
-
IDD()
-
-
BNF(int)
- Return a parameter array if BNF(), parse(), and unparse() are to be automated, null otherwise.
-
initialize(int)
- Initialize, either partially or completely.
-
parse(Parser, int)
- Parse the input file to get the parameters for this object.
-
run()
- repeatedly change x until f(x) reaches a local minimum
-
setWatchManager(WatchManager, String)
- Register all variables with this WatchManager.
-
unparse(Unparser, int)
- Output a description of this object that can be parsed with parse().
errFun
protected ErrFun errFun
- the error function to minimize
theta
protected NumExp theta
- the learning rate, a small positive number
alphas
protected MatrixD alphas
- the learning rates, alpha = e^beta(i)
pAlphas
protected PMatrixD pAlphas
- a pointer to alphas
betas
protected MatrixD betas
- the beta matrix
pBetas
protected PMatrixD pBetas
- a pointer to the betas
weightChange1
protected MatrixD weightChange1
- the change in the weights at time t
weightChange2
protected MatrixD weightChange2
- the change in the weights at time t+1
error
protected PDouble error
- a noisy estimate of the error being gradient descended on
smoothedError
protected PDouble smoothedError
- an exponentially smoothed estimate of the error
smoothingFactor
protected NumExp smoothingFactor
- the constant used to smooth the error (near 1 = long halflife)
tolerance
protected NumExp tolerance
- stop learning when smoothed error < tolerance
logSmoothedError
protected PDouble logSmoothedError
- log base 10 of the smoothed error
time
protected PInt time
- current time (time increments once per weight change
rndCopy
protected Random rndCopy
- a copy of the generator passed to evaluate(). Is used to generate the same inputs when evaluate is
called a second time.
IDD
public IDD()
setWatchManager
public void setWatchManager(WatchManager wm,
String name)
- Register all variables with this WatchManager.
This will be called after all parsing is done.
- Overrides:
- setWatchManager in class GradDesc
run
public void run()
- repeatedly change x until f(x) reaches a local minimum
- Overrides:
- run in class GradDesc
BNF
public String BNF(int lang)
- Return a parameter array if BNF(), parse(), and unparse() are to be automated, null otherwise.
- Overrides:
- BNF in class GradDesc
- See Also:
- getParameters
public
unparse
public void unparse(Unparser u,
int lang)
- Output a description of this object that can be parsed with parse().
- Overrides:
- unparse in class GradDesc
- See Also:
- Parsable
parse
public Object parse(Parser p,
int lang) throws ParserException
- Parse the input file to get the parameters for this object.
- Throws: ParserException
- parser didn't find the required token
- Overrides:
- parse in class GradDesc
initialize
public void initialize(int level)
- Initialize, either partially or completely.
- Overrides:
- initialize in class Experiment
- See Also:
- initialize
All Packages Class Hierarchy This Package Previous Next Index