// system parameter
double L,tau,D; 			// units
double dt,R_target;			// other parameters
double Pe,v,ell,D_theta;	// ABP parameters
int N_runs,N_episodes;		// RL parameters
int const_initial_policy;
double time_single_episode,max_phase_duration,reward,gammma,eta;
double pBP,pABP;
int Nt_single_episode,Nt_max_phase_duration;
int Nphi,Na,Ns;				// environment parameters

// arrays initialization
double ** target_times;
double * avg_target_times;
double ** H;
double ** H0;
double ** G;
double ** Pvalues;
double ** Svalues;
double * avg_Pvalues;
double ** avg_Pvalues_episode;
double ** avg_H0values_episode;
double ** avg_H1values_episode;
double ** avg_state_action_values;
double ** avg_glow;
int ** changes_in_G;
double * v_factor1;
double * v_factor2;
double * H2;
int * visited_states;
int * visited_actions;
double * vBP;
double * vABP;

// functions
void ProjectiveSimulationOptimized(int i);
void ProjectiveSimulationOptimized_restart(int i);
void read_parameters();
void array_initialization();
void print_averages ();
void print_data ();
void print_initial_policy();


// to parallelize and restart
int k_bunch,N_runs0,N_episodes0;
double *** H_restart;
void read_H_restart();