Package MACS

Interface Summary
RuleBasedSystem This interface is used to generalize the notion of LCS.
 

Class Summary
AbstractPlanner The AbstractPlanner class is in charge of defining the iteration strategy for the planning steps, either Random or Systematic.
ActionTable The ActionTable class is in charge of storing the number of instances of actions performed for each action for each known perception
AnticipationLearningManager This class is used to represent the AnticipationLearningManager in MACS.
AnticipationList This class is used to represent a list of Anticipations.
Anticipator The AnticipatedSituationMap class is used to store temporarily the list of anticipated situations computed from each perception through the model of transitions.
AnticipatoryClassifierList This class is intended to store a list of AnticipatoryClassifier.
ClassifierList This class is used to represent a list of classifiers.
ClassifierSystem This class is used to represent a list of anticipatory classifiers and contains methods used in LCSs.
ClassifierSystemLoader This class is used to load a classifier system from a file.
ClassifierSystemParameters This class is used to store all the parameters used in MACS.
ClassifierSystemTraceManager This class is used to trace the behavior of the LCS.
ConditionCoveringManager The ConditionCoveringManager class is in charge of adding new classifiers when no one matches the last situation experienced.
CoupleDoubles This class implements a pair of values to store immediate and expected values in models of payoffs.
CouplePF This class implements a pair to store models of payoffs in TreeMaps.
ExploMemory The ExploMemory class implements a memory of all actions performed in all known situation.
FinalStateModel This class stores informations about which states are final in the problem.
GeneralizationManager The GeneralizationManager class is in charge of generalizing classifiers in the model of transitions.
HierarchicalAgregator The HierarchicalAgregator class is in charge of choosing the next action depending on several models of payoff.
InfoValueEstimator The InfoValueEstimator class is in charge of returning the estimated immediate information value in the current situation from the informations provided by the Integrator.
Integrator The Integrator class is in charge of merging the partial anticipations of a list of classifiers so as to predict the situations that the agent may reach at the next time step.
MACSActionSelector The MACSActionSelector class is in charge of choosing the next action both in the context of actual action and in the context of "mental" propagation of values.
ModularClassifierSystem This class is the main class of MACS.
ModularClassifierSystemTraceManager This class is used to trace the behavior of MACS.
MultiModelOfPayoff This class takes care of the three models of payoff used by MACS.
PayoffModel The PayoffModel class implements a list of immediate values and expected values associated to each possible perception.
PerceptionList This class represents a list of Perceptions.
PerceptionSet This class represents a set of Perceptions.
PossibleTokenMap This class is used to store possible tokens in the Integrator.
RandomPlanner The RandomPlanner class defines the random choice of planning steps.
SpecializationManager The SpecializationManager class is in charge of specializing classifiers in the model of transitions.
SystematicPlanner The SystematicPlanner class defines the systematic choice of planning steps.