params.json

{
	// Number of recordings held in the Archive.
	// "archiveSize" : 50, // Default value
	"archiveSize": 2000,
	// Probability of archiving the result of each Program execution.
	// "archivingProbability" : 0.05, // Default value
	"archivingProbability": 0.01,
	// Boolean used to activate an evaluation of the surviving roots in validation
	// mode after the training at each generation.
	// "doValidation" : false, // Default value
	"doValidation": false,
	// Maximum number of actions performed on the learning environment during the
	// each evaluation of a root.
	// "maxNbActionsPerEval" : 1000, // Default value
	"maxNbActionsPerEval": 1500,
	// Maximum number of times a given root is evaluated.After this number is
	// reached, possibly after several generations, the score of the root will be
	// fixed, and no further evaluation will be done.
	// "maxNbEvaluationPerPolicy" : 1000, // Default value
	"maxNbEvaluationPerPolicy": 10,
	"mutation": {
		"prog": {
			// Maximum constant value possible.
			// "maxConstValue" : 100, // Default value
			"maxConstValue": 10,
			// Maximum number of Line within the Program of the TPG.
			// "maxProgramSize" : 96, // Default value
			"maxProgramSize": 20,
			// Minimum constant value possible.
			// "minConstValue" : -10, // Default value
			"minConstValue": -10,
			// Probability of inserting a line in the Program.
			// "pAdd" : 0.5, // Default value
			"pAdd": 0.5,
			// Probability of each constant to be mutated.
			// "pConstantMutation" : 0.5, // Default value
			"pConstantMutation": 0.5,
			// Probability of deleting a line of the Program.
			// "pDelete" : 0.5, // Default value
			"pDelete": 0.5,
			// Probability of altering a line of the Program.
			// "pMutate" : 1.0, // Default value
			"pMutate": 1.0,
			// Probability of creating a new program.
			// "pNewProgram" : 0.0, // Default value
			"pNewProgram": 0.0,
			// Probability of swapping two lines of the Program.
			// "pSwap" : 1.0, // Default value
			"pSwap": 1.0
		},
		"tpg": {
			// When a Program is mutated, makes sure its behavior is no longer the same.
			// "forceProgramBehaviorChangeOnMutation" : false, // Default value
			"forceProgramBehaviorChangeOnMutation": false,
			// Number of root TPGTeams at the initialisation of a TPGGraph.
			// If 0, if will be init to the number of surviving roots
			// "nbRoots" : 0, // Default value
			"initNbRoots": 0,
			// Maximum number of TPGEdge connected to each TPGTeam of the TPGGraph when
			// initialized.
			// "maxInitOutgoingEdges" : 3, // Default value
			"maxInitOutgoingEdges": 3,
			// Maximum number of outgoing edge during TPGGraph mutations.
			// "maxOutgoingEdges" : 5, // Default value
			"maxOutgoingEdges": 5,
			// Number of root TPGTeams to maintain when populating the TPGGraph
			// "nbRoots" : 100, // Default value
			"nbRoots": 150,
			// Probability of adding an outgoing Edge to a Team.
			// "pEdgeAddition" : 0.7, // Default value
			"pEdgeAddition": 0.7,
			// Probability of deleting an outgoing Edge of a Team.
			// "pEdgeDeletion" : 0.7, // Default value
			"pEdgeDeletion": 0.7,
			// Probability of changing the destination of an Edge.
			// "pEdgeDestinationChange" : 0.1, // Default value
			"pEdgeDestinationChange": 0.1,
			// Probability of the new destination of an Edge to be an Action.
			// "pEdgeDestinationIsAction" : 0.5, // Default value
			"pEdgeDestinationIsAction": 0.5,
			// Probability of mutating the Program of an outgoing Edge.
			// "pProgramMutation" : 0.2, // Default value
			"pProgramMutation": 0.2
		}
	},
	// Number of generations of the training.
	// "nbGenerations" : 500, // Default value
	"nbGenerations": 1200,
	// [Only used in AdversarialLearningAgent.]
	// Number of times each job is evaluated in the learning process.
	// Each root may belong to several jobs, hence this parameter should be lower
	// than the nbIterationsPerPolicyEvaluation parameter.
	// "nbIterationsPerJob" : 1, // Default value
	"nbIterationsPerJob": 1,
	// Number of evaluation of each root per generation.
	// "nbIterationsPerPolicyEvaluation" : 5, // Default value
	"nbIterationsPerPolicyEvaluation": 1,
	// Number of Constant available in each Program.
	// "nbProgramConstant" : 0, // Default value
	"nbProgramConstant": 0,
	// Number of registers for the Program execution.
	// "nbRegisters" : 8, // Default value
	"nbRegisters": 8,
	// [Only used in ParallelLearningAgent and child classes.]
	// Number of threads used for the training process.
	// When undefined in the json file, this parameter is automatically set to the
	// number of cores of the CPU.
	// /* "nbThreads" : 0,*/ // Commented by default
	/* "nbThreads" : 0,*/
	// Percentage of deleted (and regenerated) root TPGVertex at each generation.
	// "ratioDeletedRoots" : 0.5, // Default value
	"ratioDeletedRoots": 0.85
}