used for which dimension of conditions can be generalized or specialized
only record the valid dimensions which has non-zero values in its elements
1st dimension contains the indices of all the valid dimensions.
Returns the action recommendation given the array of action activations
and a limit on the length of elements in the array from position 0 those
are eligible candidates.
Returns the action recommendation given the array of action activations
and a limit on start position and end position in the array within the
range the elements are eligible candidates.
initialize the Global object associated with each agent without
using GUI.
init() -
Method in class tasksimulators.newsimu.AGL.TaskAGL
The method overrides the one in Task, it implements the process of
initialization of Global objects assoicated with the running agents
by loading the existing setting groups from the hard disk.
init() -
Method in class tasksimulators.newsimu.PC.TaskPC
The method overrides the one in Task, it implements the process of
initialization of Global objects assoicated with the running agents
by loading the existing setting groups from the hard disk.
init() -
Method in class tasksimulators.newsimu.XOR.TaskXOR
Loads the agent settings from the configuration files.
observe new sensory input, new GS and WM states if exists and deliver them
to each active network and form new state including the three types of inputs
if exists.
Selects randomly one action from the action-decision network (such as EX,
GS, WM action-decision network) using "randomly selected" approach based
on a chosen component.
Selects one action from the action-decision network (such as EX, GS, WM
action-decision network) using "boltzmann distribution based on utility"
approach based on a chosen component.
Selects one action from the action-decision network (such as EX, GS, WM
action-decision network) using "boltzmann distribution based on utility"
approach based on a chosen component.
using "radomly selected" approach to select one component on which the
chosen actions are based, such as action chosing is based on BL, FR, RER,
IRL etc.
start() -
Method in class tasksimulators.newsimu.XOR.TaskXOR
The method overrides the one in Task, it implements the process of
initialization of Global objects assoicated with the running agents
by loading the existing setting groups from the hard disk.