[This is preliminary documentation and is subject to change.]
This class serves as the base template class for a reinforcement-trainable backpropagation network (e.g., SimplifiedQBPNetwork, QBPNetwork)
in the CLARION Library
The ReinforcementTrainableBPNetwork..::..ReinforcementTrainableBPNetworkParameters type exposes the following members.
Constructors
Name | Description | |
---|---|---|
![]() |
ReinforcementTrainableBPNetwork..::..ReinforcementTrainableBPNetworkParameters(Boolean) |
Initializes a parameters class for a ReinforcementTrainableBPNetwork
|
![]() |
ReinforcementTrainableBPNetwork..::..ReinforcementTrainableBPNetworkParameters(ReinforcementTrainableBPNetwork..::..ReinforcementTrainableBPNetworkParameters, Boolean) |
Initializes a parameters class for a ReinforcementTrainableBPNetwork and sets the values of the parameters to the values specified
|
Methods
Name | Description | |
---|---|---|
![]() |
Global_OnParameterChanged |
The event method used for performing global parameter changes
(Inherited from ClarionComponent..::..ClarionComponentParameters.) |
Properties
Name | Description | |
---|---|---|
![]() |
ELIGIBILITY |
A switch that can be used to specify eligibility (in the absence of a more sophisticated eligibility method)
|
![]() |
EXTRACTION_PROBABILITY |
The extraction probability (i.e., the probability a rule will be extracted)
|
![]() |
INITIAL_THRESHOLDS_LOWER_BOUND |
The low bound for the initial threshold
|
![]() |
INITIAL_THRESHOLDS_UPPER_BOUND |
The upper bound for the initial threshold
|
![]() |
INITIAL_WEIGHTS_LOWER_BOUND |
The low bound for the initial weights
|
![]() |
INITIAL_WEIGHTS_UPPER_BOUND |
The upper bound for the initial weights
|
![]() |
IsGlobal |
Used to specify whether the particular instance of the parameters class is being used for global or local parameters
(Inherited from ClarionComponent..::..ClarionComponentParameters.) |
![]() |
LEARNING_RATE |
The learning rate (used for learning)
|
![]() |
MOMENTUM |
The momentum (used for learning)
|
![]() |
POSITIVE_MATCH_THRESHOLD |
The threshold for the positive match criterion
|
![]() |
R_ZERO |
The error tolerance (used for learning)
|