[This is preliminary documentation and is subject to change.]
This class implements the Action Centered Subsystem (ACS) in the Clarion Library
The ActionCenteredSubsystem..::..ActionCenteredSubsystemParameters type exposes the following members.
Properties
Name | Description | |
---|---|---|
![]() |
A |
The constant A used to factor in the MCS measure when calculating the probability or weight of for the bottom level
during level selection
|
![]() |
B |
The constant B used to factor in the MCS measure when calculating the probability or weight of for the bottom level
during level selection
|
![]() |
BOTTOM_LEVEL_DECISION_TIME |
The decision time for the bottom level of the ACS
|
![]() |
C3 |
The C3 constant used for variable level selection
|
![]() |
C4 |
The C4 constant used for variable level selection
|
![]() |
DEFAULT_ACTION_POTENTIAL |
Specifies the default activation to set for the DO_NOTHING external action chunk (if no IDNs are eligible to be used)
when calculating action potential
|
![]() |
DELETION_FREQUENCY |
The frequency (in terms of # of learning steps) in which deletions by density are to be performed
|
![]() |
DISCOUNT |
The match discount factor to be applied at the end of an episode
|
![]() |
EXTERNAL_ACTION_PROBABILITY |
The probability of choosing an external action
|
![]() |
FIXED_BL_LEVEL_SELECTION_MEASURE |
The fixed selection measure for the bottom level
|
![]() |
FIXED_FR_LEVEL_SELECTION_MEASURE |
The fixed selection measure for the fixed rules
|
![]() |
FIXED_IRL_LEVEL_SELECTION_MEASURE |
The fixed selection measure for the IRL rules
|
![]() |
FIXED_RER_LEVEL_SELECTION_MEASURE |
The fixed selection measure for the RER rules
|
![]() |
GS_UPDATE_ACTION_PROBABILITY |
The probability of choosing a goal structure update action
|
![]() |
LEVEL_SELECTION_METHOD |
Specifies the method to use for level selection
|
![]() |
LEVEL_SELECTION_OPTION |
Specifies the option to use for level selection
|
![]() |
LOCAL_EPISODIC_MEMORY_RETENTION_THRESHOLD |
The maximum number of time steps (since the most recent) that local episodic memory should be kept before being discarded
|
![]() |
MAXIMUM_DECISION_TIME |
The maximum decision-time for the ACS
|
![]() |
MCS_BL_SELECTION_MEASURE |
The level selection measure specified by the the MCS (used for selecting the bottom level of the ACS)
|
![]() |
MCS_FR_SELECTION_MEASURE |
The level selection measure specified by the the MCS (used for selecting the bottom level of the ACS)
|
![]() |
MCS_IRL_SELECTION_MEASURE |
The level selection measure specified by the the MCS (used for selecting the bottom level of the ACS)
|
![]() |
MCS_MAXIMUM_DECISION_TIME |
The maximum decision-time as reported by the MCS
|
![]() |
MCS_RER_SELECTION_MEASURE |
The level selection measure specified by the the MCS (used for selecting the bottom level of the ACS)
|
![]() |
NACS_REASONING_ACTION_PROBABILITY |
The probability of choosing an NACS reasoning action
|
![]() |
NACS_RETRIEVE_ACTION_PROBABILITY |
The probability of choosing an NACS retrieve action
|
![]() |
PARAMETER_CHANGE_ACTION_PROBABILITY |
The probability of choosing a parameter change action
|
![]() |
PERFORM_BL_LEARNING |
Specifies whether or not bottom level learning should be performed
|
![]() |
PERFORM_DELETION_BY_DENSITY |
Specifies whether or not intermittent rule deletion by density should be performed
|
![]() |
PERFORM_IRL_REFINEMENT |
Specifies whether or not IRL rule refinement should be performed
|
![]() |
PERFORM_LEARNING |
Specifies whether or not learning in general (including extraction, refinement, bottom-level learning, deletion by density, etc.)
should be performed
|
![]() |
PERFORM_RER_REFINEMENT |
Specifies whether or not RER rule refinement should be performed
|
![]() |
PERFORM_RULE_EXTRACTION |
Specifies whether or not rule extraction should be performed
|
![]() |
PERFORM_TOP_DOWN_LEARNING |
Specifies whether or not top-down learning should be performed
|
![]() |
PERSISTENCE |
The persistence factor for the previous selection
|
![]() |
POSITIVE_MATCH_THRESHOLD |
The threshold for the positive match criterion of the top and bottom level component collections
|
![]() |
SELECTION_TEMPERATURE |
The temperature for stochastic selection
|
![]() |
SELECTION_THRESHOLD |
The threshold for stochastic selection
|
![]() |
TOP_LEVEL_DECISION_TIME |
The decision time for the top level of the ACS
|
![]() |
USE_ACTION_POTENTIAL |
Specifies whether action potential should be calculated by the ACS during perception
|
![]() |
USE_ACTION_PROBABILITIES |
Specifies whether action type selection (based on probability) should be performed
|
![]() |
VARIABLE_BL_BETA |
The bottom level beta for variable level selection
|
![]() |
VARIABLE_FR_BETA |
The fixed rule beta for variable level selection
|
![]() |
VARIABLE_IRL_BETA |
The IRL beta for variable level selection
|
![]() |
VARIABLE_RER_BETA |
The RER beta for variable level selection
|
![]() |
WM_UPDATE_ACTION_PROBABILITY |
The probability of choosing a working memory update action
|
![]() |
WORKING_MEMORY_CAPACITY |
The maximum number of slots for working memory (i.e., the maximum number of chunks that can be in working memory)
|