params.json

{
	// #ifdef SOLUTION_STRENGTHENING
	// Boolean used to activate an evaluation of the surviving roots in validation
	// mode after the training at each generation.
	// "doValidation" : false, // Default value
	"doValidation": true,
	// #endif // SOLUTION_STRENGTHENING
	// Maximum number of actions performed on the learning environment during the
	// each evaluation of a root.
	// "maxNbActionsPerEval" : 1000, // Default value
	"maxNbActionsPerEval": 1500,
	// #ifdef SOLUTION_STRENGTHENING
	// 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,
	// #endif // SOLUTION_STRENGTHENING
	"mutation": {
		"tpg": {
			// Number of root TPGTeams to maintain when populating the TPGGraph
			// "nbRoots" : 100, // Default value
			"nbRoots": 150
		}
	},
	// Number of generations of the training.
	// "nbGenerations" : 500, // Default value
	"nbGenerations": 1200,
	// Number of evaluation of each root per generation.
	// "nbIterationsPerPolicyEvaluation" : 5, // Default value
	//#ifdef SOLUTION_STRENGTHENING
	"nbIterationsPerPolicyEvaluation": 5,
	//#else // SOLUTION_STRENGTHENING
	"nbIterationsPerPolicyEvaluation": 1,
	//#endif // SOLUTION_STRENGTHENING
}