int main(int argc , char **argv)
{
int i , j , t , targetlen , parent_a , parent_b ;
int *numcorrect;
char **newpop , **oldpop , **swap;
double *normfit;
//srandom(seed);
srand((unsigned)time(NULL));
// whether to consider forcing the size to be even .
targetlen = 10;
printf("hello! \n");
newpop = malloc(sizeof(char *) * size);
oldpop = malloc(sizeof(char *) * size);
printf("hello 1-1 \n");
numcorrect = malloc(sizeof(int) * size);
normfit = malloc(sizeof(double) * size);
printf("hello2 \n");
for(i = 0 ; i < size ; i++)
{
newpop[i] = malloc(sizeof(char) * targetlen + 1);
oldpop[i] = malloc(sizeof(char) * targetlen + 1);
for(j = 0 ; j < targetlen ; j++)
{
oldpop[i][j] = random_letter_or_space();
}
newpop[i][targetlen] = 0;
oldpop[i][targetlen] = 0;
}
for(t = 0 ; t < steps ; t++)
{
compute_fitness(oldpop , numcorrect , normfit);
dump_stats(numcorrect , oldpop , t + 1 , targetlen);
for(i = 0 ; i < size ; i += 2)
{
parent_a = select_one(normfit);
parent_b = select_one(normfit);
// whether to add parent_a can not be equal to parent_b .
//printf("p_a = %d , p_b = %d \n" , parent_a , parent_b);
reproduce(oldpop , newpop , parent_a , parent_b , targetlen , i);
}
swap = oldpop;
oldpop = newpop;
newpop = swap;
/*
swap = newpop;
newpop = oldpop;
oldpop = swap;
*/
}
exit(0);
}
int main(int argc, char *args[]) {
char buffer[255]; // Buffer for sending data
int i; // Index
if (argc == 4) { // Get parameters
offset = atoi(args[1]);
migrx = atof(args[2]);
migrz = atof(args[3]);
//migration goal point comes from the controller arguments. It is defined in the world-file, under "controllerArgs" of the supervisor.
printf("Migratory instinct : (%f, %f)\n", migrx, migrz);
} else {
printf("Missing argument\n");
return 1;
}
orient_migr = -atan2f(migrx,migrz);
if (orient_migr<0) {
orient_migr+=2*M_PI; // Keep value within 0, 2pi
}
reset();
send_init_poses();
// Compute reference fitness values
float fit_cluster; // Performance metric for aggregation
float fit_orient; // Performance metric for orientation
for(;;) {
wb_robot_step(TIME_STEP);
if (t % 10 == 0) {
for (i=0;i<FLOCK_SIZE;i++) {
// Get data
loc[i][0] = wb_supervisor_field_get_sf_vec3f(robs_trans[i])[0]; // X
loc[i][1] = wb_supervisor_field_get_sf_vec3f(robs_trans[i])[2]; // Z
loc[i][2] = wb_supervisor_field_get_sf_rotation(robs_rotation[i])[3]; // THETA
// Sending positions to the robots, comment the following two lines if you don't want the supervisor sending it
sprintf(buffer,"%1d#%f#%f#%f##%f#%f",i+offset,loc[i][0],loc[i][1],loc[i][2], migrx, migrz);
wb_emitter_send(emitter,buffer,strlen(buffer));
}
//Compute and normalize fitness values
compute_fitness(&fit_cluster, &fit_orient);
fit_cluster = fit_cluster_ref/fit_cluster;
fit_orient = 1-fit_orient/M_PI;
printf("time:%d, Topology Performance: %f\n", t, fit_cluster);
}
t += TIME_STEP;
}
}
//
// Trial to test the robot's behavior (according to NN) in the environment
//
double run_trial() {
double inputs[NB_INPUTS];
double outputs[NB_OUTPUTS];
//Get position of the e-puck
static double position[3]={0.0,0.0,0.0};
const double *gps_matrix = wb_gps_get_values(gps);
position[0] = gps_matrix[0];//gps_position_x(gps_matrix);
position[1] = gps_matrix[2];//gps_position_z(gps_matrix);
position[2] = gps_matrix[1];//gps_position_y(gps_matrix);
//Speed of the robot's wheels within the +SPEED_RANGE and -SPEED_RANGE values
int speed[2]={0,0};
//Maximum activation of all IR proximity sensors [0,1]
double maxIRActivation = 0;
//get sensor data, i.e., NN inputs
int i, j;
for(j=0;j<NB_INPUTS;j++) {
inputs[j]=(((double)wb_distance_sensor_get_value(ps[j])-ps_offset[j])<0)?0:((double)wb_distance_sensor_get_value(ps[j])-ps_offset[j])/((double)PS_RANGE);
//get max IR activation
if(inputs[j]>maxIRActivation) maxIRActivation=inputs[j];
printf("sensor #: %d, sensor read: %g, maxIR: %g\n", j, inputs[j], maxIRActivation);
}
//printf("max IR activation: %f\n", maxIRActivation);
// Run the neural network and computes the output speed of the robot
run_neural_network(inputs, outputs);
speed[LEFT] = SPEED_RANGE*outputs[0];
speed[RIGHT] = SPEED_RANGE*outputs[1];
// If you are running against an obstacle, stop the wheels
if ( maxIRActivation > 0.9 ) {
speed[LEFT]=0;
speed[RIGHT]=0;
}
// Set wheel speeds to output values
wb_differential_wheels_set_speed(speed[LEFT], speed[RIGHT]); //left, right
// Stop the robot if it is against an obstacle
for (i=0;i<NB_DIST_SENS;i++) {
int tmpps=(((double)wb_distance_sensor_get_value(ps[i])-ps_offset[i])<0)?0:((double)wb_distance_sensor_get_value(ps[i])-ps_offset[i]);
if(OBSTACLE_THRESHOLD<tmpps ) {// proximity sensors
//printf("%d \n",tmpps);
speed[LEFT] = 0;
speed[RIGHT] = 0;
break;
}
}
return compute_fitness(speed, position, maxIRActivation);
}
double run_trial() {
int speed[2]={0,0};
//Maximum activation of all IR proximity sensors [0,1]
//double maxIRActivation = 0;
//get sensor data, i.e., NN inputs
int j;
for(j=0;j<NB_DIST_SENS;j++) {
//printf("sensor %d reads %g\n",j,wb_distance_sensor_get_value(ps[j]));
temp[j]=(((double)wb_distance_sensor_get_value(ps[j])-ps_offset[j])<0)?0:(((double)wb_distance_sensor_get_value(ps[j])-ps_offset[j])/((double)PS_RANGE));
}
for(j=0;j<NB_PS;j++) {
//printf("sensor %d reads %g\n",j,wb_distance_sensor_get_value(ps[j]));
inputs[j]=(temp[2*j]+temp[(2*j)+1])/2.0;
}
inputs[4]= wb_distance_sensor_get_value(fs[0])-fs_offset[0];
//printf("floor sensor:%g\n",inputs[4]);
// Run the neural network and computes the output speed of the robot
run_neural_network(inputs, outputs);
speed[LEFT] = clip_value(outputs[0],max_speed); //scale outputs between 0 and 1
speed[RIGHT] = clip_value(outputs[1],max_speed);
//printf("L: %d; R: %d\n",speed[LEFT],speed[RIGHT]);
// Set wheel speeds to output values
wb_differential_wheels_set_speed(speed[LEFT], speed[RIGHT]); //left, right
//printf("Set wheels to outputs.\n");
return compute_fitness(inputs[4]);
return compute_fitness(inputs[4]);
}
int main(int argc, char **argv)
{
int i, j, t, parent_a, parent_b;
char **swap, **newpop, **oldpop;
double *fit, *normfit;
get_options(argc, argv, options, help_string);
srandom(seed);
/* Force the size to be even. */
size += (size / 2 * 2 != size);
/* Initialize the population. */
newpop = xmalloc(sizeof(char *) * size);
oldpop = xmalloc(sizeof(char *) * size);
fit = xmalloc(sizeof(double) * size);
normfit = xmalloc(sizeof(double) * size);
for(i = 0; i < size; i++) {
newpop[i] = xmalloc(sizeof(char) * len + 1);
oldpop[i] = xmalloc(sizeof(char) * len + 1);
for(j = 0; j < len; j++)
oldpop[i][j] = random() % 2 + '0';
oldpop[i][len] = 0;
newpop[i][len] = 0;
}
/* For each time step... */
for(t = 0; t < gens; t++) {
compute_fitness(oldpop, fit, normfit);
dump_stats(t, oldpop, fit);
/* Pick two parents by fitness and mate them until the
* next generation has been made.
*/
for(i = 0; i < size; i += 2) {
parent_a = select_one(normfit);
parent_b = select_one(normfit);
reproduce(oldpop, newpop, parent_a, parent_b, i);
}
/* Make everything old new again. */
swap = newpop; newpop = oldpop; oldpop = swap;
}
exit(0);
}
void EXP_Class::adv ( void ){
//cout << "enter advance" << endl;
if( viewing ) stop_iterations_loop( );
update_sensors( );//here you compute the input vector
update_controllers ( ); //here you update the controllers and you generate a new output vector
if( viewing ) param->eye->view_eye_movement();
update_world(); //Here you call the set eye fucntion to upadte the eye position given the output vector
//manage_collisions ( );
compute_fitness();
iter++;
//cout << "leave advance" << endl;
}
//---------------------------------------------------------------------------
void start_steady_state(t_parameters ¶ms, t_graph *training_graphs, int num_training_graphs, t_graph *validation_graphs, int num_validation_graphs, int num_variables, int num_procs, int current_proc_id)
{
int size_to_send = params.code_length * sizeof(t_code3) + params.num_constants * 20 + 20;
char *s_source = new char[size_to_send];
char *s_dest = new char[size_to_send];
t_chromosome receive_chromosome;
allocate_chromosome(receive_chromosome, params);
// a steady state model -
// Newly created inviduals replace the worst ones (if the offspring are better) in the same (sub) population.
// allocate memory for all sub populations
t_chromosome **sub_populations; // an array of sub populations
sub_populations = new t_chromosome*[params.num_sub_populations];
for (int p = 0; p < params.num_sub_populations; p++) {
sub_populations[p] = new t_chromosome[params.sub_population_size];
for (int i = 0; i < params.sub_population_size; i++)
allocate_chromosome(sub_populations[p][i], params); // allocate each individual in the subpopulation
}
#ifdef USE_THREADS
// allocate memory
double** vars_values = new double*[params.num_threads];
for (int t = 0; t < params.num_threads; t++)
vars_values[t] = new double[num_variables];
// an array of threads. Each sub population is evolved by a thread
std::thread **mep_threads = new std::thread*[params.num_threads];
// we create a fixed number of threads and each thread will take and evolve one subpopulation, then it will take another one
std::mutex mutex;
// we need a mutex to make sure that the same subpopulation will not be evolved twice by different threads
#else
double* vars_values = new double[num_variables];
#endif
t_chromosome best_validation;
allocate_chromosome(best_validation, params);
double best_validation_fitness = DBL_MAX;
// evolve for a fixed number of generations
for (int generation = 0; generation < params.num_generations; generation++) { // for each generation
#ifdef USE_THREADS
int current_subpop_index = 0;
for (int t = 0; t < params.num_threads; t++)
mep_threads[t] = new std::thread(evolve_one_subpopulation, ¤t_subpop_index, &mutex, sub_populations, generation, ¶ms, training_graphs, num_training_graphs, num_variables, vars_values[t]);
for (int t = 0; t < params.num_threads; t++) {
mep_threads[t]->join();
delete mep_threads[t];
}
#else
//for (int p = 0; p < params.num_sub_populations; p++)
int p = 0;
evolve_one_subpopulation(&p, sub_populations, generation, ¶ms, training_graphs, num_training_graphs, num_variables, vars_values);
#endif
// find the best individual
int best_individual_subpop_index = 0; // the index of the subpopulation containing the best invidual
for (int p = 1; p < params.num_sub_populations; p++)
if (sub_populations[p][0].fitness < sub_populations[best_individual_subpop_index][0].fitness)
best_individual_subpop_index = p;
double *partial_values_array = new double[params.code_length];
sub_populations[best_individual_subpop_index][0].simplify(params.code_length);
double current_validation_fitness = compute_fitness(sub_populations[best_individual_subpop_index][0], validation_graphs, num_validation_graphs, num_variables, vars_values, partial_values_array);
if (!generation || generation && current_validation_fitness < best_validation_fitness) {
best_validation_fitness = current_validation_fitness;
copy_individual(best_validation, sub_populations[best_individual_subpop_index][0], params);
}
delete[] partial_values_array;
printf("proc_id=%d, generation=%d, best training =%lf best validation =%lf\n", current_proc_id, generation, sub_populations[best_individual_subpop_index][0].fitness, best_validation_fitness);
if (current_proc_id == 0) {
FILE* f = fopen("tst_log.txt", "a");
fprintf(f, "proc_id=%d, generation=%d, best=%lf\n", current_proc_id, generation, sub_populations[best_individual_subpop_index][0].fitness);
fclose(f);
}
// now copy one individual from one population to the next one.
// the copied invidual will replace the worst in the next one (if is better)
for (int p = 0; p < params.num_sub_populations; p++) {
int k = rand() % params.sub_population_size;// the individual to be copied
// replace the worst in the next population (p + 1) - only if is better
int index_next_pop = (p + 1) % params.num_sub_populations; // index of the next subpopulation (taken in circular order)
if (sub_populations[p][k].fitness < sub_populations[index_next_pop][params.sub_population_size - 1].fitness) {
copy_individual(sub_populations[index_next_pop][params.sub_population_size - 1], sub_populations[p][k], params);
qsort((void *)sub_populations[index_next_pop], params.sub_population_size, sizeof(sub_populations[0][0]), sort_function);
}
}
#ifdef USE_MPI
// here I have to copy few individuals from one process to another process
for (int i = 0; i < 1; i++) {
int source_sub_population_index = rand() % params.num_sub_populations;
int chromosome_index = rand() % params.sub_population_size;
int tag = 0;
sub_populations[source_sub_population_index][chromosome_index].to_string(s_dest, params.code_length, params.num_constants);
MPI_Send((void*)s_dest, size_to_send, MPI_CHAR, (current_proc_id + 1) % num_procs, tag, MPI_COMM_WORLD);
MPI_Status status;
int flag;
MPI_Iprobe(!current_proc_id ? num_procs - 1 : current_proc_id - 1, tag, MPI_COMM_WORLD, &flag, &status);
if (flag) {
MPI_Recv(s_source, size_to_send, MPI_CHAR, !current_proc_id ? num_procs - 1 : current_proc_id - 1, tag, MPI_COMM_WORLD, &status);
receive_chromosome.from_string(s_source, params.code_length, params.num_constants);
int dest_sub_population_index = rand() % params.num_sub_populations;
if (receive_chromosome.fitness < sub_populations[dest_sub_population_index][params.sub_population_size - 1].fitness) {
copy_individual(sub_populations[dest_sub_population_index][params.sub_population_size - 1], receive_chromosome, params);
qsort((void *)sub_populations[dest_sub_population_index], params.sub_population_size, sizeof(sub_populations[0][0]), sort_function);
}
}
}
#endif
}
#ifdef USE_THREADS
delete[] mep_threads;
#endif
// print best t_chromosome
// any of them can be printed because if we allow enough generations, the populations will become identical
print_chromosome(best_validation, params, num_variables);
best_validation.to_file_simplified("best.txt", params.code_length, params.num_constants);
// free memory
for (int p = 0; p < params.num_sub_populations; p++) {
for (int i = 0; i < params.sub_population_size; i++)
delete_chromosome(sub_populations[p][i]);
delete[] sub_populations[p];
}
delete[] sub_populations;
#ifdef USE_THREADS
for (int t = 0; t < params.num_threads; t++)
delete[] vars_values[t];
delete[] vars_values;
#endif
delete[] s_dest;
delete[] s_source;
delete_chromosome(receive_chromosome);
delete_chromosome(best_validation);
}
void evolve_one_subpopulation(int *current_subpop_index, t_chromosome ** sub_populations, int generation_index, t_parameters *params, t_graph *training_graphs, int num_training_graphs, int num_variables, double* vars_values)
#endif
{
int pop_index = 0;
while (*current_subpop_index < params->num_sub_populations) {// still more subpopulations to evolve?
#ifdef USE_THREADS
while (!mutex->try_lock()) {}// create a lock so that multiple threads will not evolve the same sub population
pop_index = *current_subpop_index;
(*current_subpop_index)++;
mutex->unlock();
#else
pop_index = *current_subpop_index;
(*current_subpop_index)++;
#endif
// pop_index is the index of the subpopulation evolved by the current thread
if (pop_index < params->num_sub_populations) {
t_chromosome *a_sub_population = sub_populations[pop_index];
t_chromosome offspring1, offspring2;
allocate_chromosome(offspring1, *params);
allocate_chromosome(offspring2, *params);
double *partial_values_array = new double[params->code_length];
if (generation_index == 0) {
for (int i = 0; i < params->sub_population_size; i++) {
generate_random_chromosome(a_sub_population[i], *params, num_variables);
a_sub_population[i].fitness = compute_fitness(a_sub_population[i], training_graphs, num_training_graphs, num_variables, vars_values, partial_values_array);
}
// sort ascendingly by fitness inside this population
qsort((void *)a_sub_population, params->sub_population_size, sizeof(a_sub_population[0]), sort_function);
}
else // next generations
for (int k = 0; k < params->sub_population_size; k += 2) {
// we increase by 2 because at each step we create 2 offspring
// choose the parents using binary tournament
int r1 = tournament_selection(a_sub_population, params->sub_population_size, 2);
int r2 = tournament_selection(a_sub_population, params->sub_population_size, 2);
// crossover
double p_0_1 = rand() / double(RAND_MAX); // a random number between 0 and 1
if (p_0_1 < params->crossover_probability)
one_cut_point_crossover(a_sub_population[r1], a_sub_population[r2], *params, offspring1, offspring2);
else {// no crossover so the offspring are a copy of the parents
copy_individual(offspring1, a_sub_population[r1], *params);
copy_individual(offspring2, a_sub_population[r2], *params);
}
// mutate the result and compute fitness
mutation(offspring1, *params, num_variables);
offspring1.fitness = compute_fitness(offspring1, training_graphs, num_training_graphs, num_variables, vars_values, partial_values_array);
// mutate the other offspring too
mutation(offspring2, *params, num_variables);
offspring2.fitness = compute_fitness(offspring2, training_graphs, num_training_graphs, num_variables, vars_values, partial_values_array);
// replace the worst in the population
if (offspring1.fitness < a_sub_population[params->sub_population_size - 1].fitness) {
copy_individual(a_sub_population[params->sub_population_size - 1], offspring1, *params);
qsort((void *)a_sub_population, params->sub_population_size, sizeof(a_sub_population[0]), sort_function);
}
if (offspring2.fitness < a_sub_population[params->sub_population_size - 1].fitness) {
copy_individual(a_sub_population[params->sub_population_size - 1], offspring2, *params);
qsort((void *)a_sub_population, params->sub_population_size, sizeof(a_sub_population[0]), sort_function);
}
}
delete_chromosome(offspring1);
delete_chromosome(offspring2);
delete[] partial_values_array;
}
}
}
/*
* Main function.
*/
int main(int argc, char *args[]) {
float fitness;
// The type of formation is decided by the user through the world
char* formation = DEFAULT_FORMATION;
if(argc == 2) {
formation_type = atoi(args[1]);
}
if(formation_type == 0)
formation = "line";
else if(formation_type == 1)
formation = "column";
else if(formation_type == 2)
formation = "wedge";
else if(formation_type == 3)
formation = "diamond";
printf("Chosen formation: %s.\n", formation);
////////////////////////////////////////////////////////////////////////////////////////////////////
// PSO //
////////////////////////////////////////////////////////////////////////////////////////////////////
// The paramethers that we don't optimise are commented.
// To add them to the simulation you should uncomment it here, in pso_ocba and change DIMENSIONALITY
// each motorschema's weight
parameter_ranges[0][0] = 0;
parameter_ranges[0][1] = 10;
parameter_ranges[1][0] = 0;
parameter_ranges[1][1] = 10;
parameter_ranges[2][0] = 0;
parameter_ranges[2][1] = 10;
parameter_ranges[3][0] = 0;
parameter_ranges[3][1] = 10; /*
parameter_ranges[4][0] = 0;
parameter_ranges[4][1] = 4;*/
/*
// thresholds
parameter_ranges[ 5][0] = 0.001; // obstacle avoidance min
parameter_ranges[ 5][1] = 0.5;
parameter_ranges[ 6][0] = 0.001; // obstacle avoidance min + range
parameter_ranges[ 6][1] = 1;
parameter_ranges[ 7][0] = 0.001; // move_to_goal min
parameter_ranges[ 7][1] = 0.5;
parameter_ranges[ 8][0] = 0.001; // move_to_goal min + range
parameter_ranges[ 8][1] = 1;
parameter_ranges[ 9][0] = 0.001; // avoid_robot min
parameter_ranges[ 9][1] = 0.2;
parameter_ranges[10][0] = 0.001; // avoid_robot min + range
parameter_ranges[10][1] = 1;
parameter_ranges[11][0] = 0.001; // keep_formation min
parameter_ranges[11][1] = 0.3;
parameter_ranges[12][0] = 0.001; // keep_formation min + range
parameter_ranges[12][1] = 1;
// noise
parameter_ranges[13][0] = 1; // noise_gen frequency
parameter_ranges[13][1] = 20;
parameter_ranges[14][0] = 0; // fade or not
parameter_ranges[14][1] = 1;
*/
float optimal_params[DIMENSIONALITY];
initialize();
reset();
pso_ocba(optimal_params);
// each motorschema's weight
w_goal = optimal_params[0];
w_keep_formation = optimal_params[1];
w_avoid_robot = optimal_params[2];
w_avoid_obstacles = optimal_params[3];/*
w_noise = optimal_params[4];
// thresholds
avoid_obst_min_threshold = optimal_params[5];
avoid_obst_max_threshold = optimal_params[5] + optimal_params[6];
move_to_goal_min_threshold = optimal_params[7];
move_to_goal_max_threshold = optimal_params[7] + optimal_params[8];
avoid_robot_min_threshold = optimal_params[9];
avoid_robot_max_threshold = optimal_params[9] + optimal_params[10];
keep_formation_min_threshold = optimal_params[11];
keep_formation_max_threshold = optimal_params[11] + optimal_params[12];
// noise parameters
noise_gen_frequency = optimal_params[13];
fading = round(optimal_params[14]); // = 0 or 1
*/
printf("\n\n\nThe optimal parameters are: \n");
printf("___________ w_goal...................... = %f\n", w_goal);
printf("___________ w_keep_formation............ = %f\n", w_keep_formation);
printf("___________ w_avoid_robo................ = %f\n", w_avoid_robot);
printf("___________ w_avoid_obstacles........... = %f\n", w_avoid_obstacles);
printf("___________ w_noise..................... = %f\n", w_noise);
printf("___________ noise_gen_frequency......... = %d\n", noise_gen_frequency);
printf("___________ fading...................... = %d\n", fading);
printf("___________ avoid_obst_min_threshold.... = %f\n", avoid_obst_min_threshold);
printf("___________ avoid_obst_max_threshold.... = %f\n", avoid_obst_max_threshold);
printf("___________ move_to_goal_min_threshold.. = %f\n", move_to_goal_min_threshold);
printf("___________ move_to_goal_max_threshold.. = %f\n", move_to_goal_max_threshold);
printf("___________ avoid_robot_min_threshold... = %f\n", avoid_robot_min_threshold);
printf("___________ avoid_robot_max_threshold... = %f\n", avoid_robot_max_threshold);
printf("___________ keep_formation_min_threshold = %f\n", keep_formation_min_threshold);
printf("___________ keep_formation_max_threshold = %f\n", keep_formation_max_threshold);
printf("\n\n");
////////////////////////////////////////////////////////////////////////////////////////////////////
// REAL RUN //
////////////////////////////////////////////////////////////////////////////////////////////////////
// Real simulation with optimized parameters:
initialize();
// reset and communication part
printf("Beginning of the real simulation\n");
reset_to_initial_values();
printf("Supervisor reset.\n");
send_real_run_init_poses();
printf("Init poses sent.\n Chosen formation: %s.\n", formation);
// sending weights
send_weights();
printf("Weights sent\n");
bool is_goal_reached=false;
// infinite loop
for(;;) {
wb_robot_step(TIME_STEP);
// every 10 TIME_STEP (640ms)
if (simulation_duration % 10 == 0) {
send_current_poses();
update_fitness();
}
simulation_duration += TIME_STEP;
if (simulation_has_ended()) {
is_goal_reached=true;
printf("\n\n\n\n______________________________________GOAL REACHED!______________________________________\n\n");
// stop the robots
w_goal = 0;
w_keep_formation = 0;
w_avoid_robot = 0;
w_avoid_obstacles = 0;
w_noise = 0;
send_weights();
break;
}
}
if (is_goal_reached){
fitness = compute_fitness(FORMATION_SIZE,loc);
} else {
fitness = compute_fitness(FORMATION_SIZE,loc);
}
printf("fitness = %f\n",fitness);
while (1) wb_robot_step(TIME_STEP); //wait forever
return 0;
}
int SSrun_scatter_search(SS *scatter_search, CCutil_timer *timer) {
guint i;
REFSET *refset = scatter_search->rs;
int flag, val = 0;
int nbnew_sol = 0;
int nbjobs = scatter_search->njobs;
int nmachines = scatter_search->nmachines;
int nb_noimprovements = 0;
int *totsubset = (int *) NULL;
double limit = scatter_search->timelimit;
totsubset = CC_SAFE_MALLOC(scatter_search->b1 + 1, int);
CCcheck_NULL_2(totsubset, "Failed tot allocate memory to tot subset");
if (refset->list1->len == 0) {
printf("We can't run scatter search, refset is empty\n");
val = 1;
goto CLEAN;
}
printf("PMCombination method\n");
CCutil_suspend_timer(timer);
CCutil_resume_timer(timer);
while (refset->newsol && scatter_search->status != opt &&
timer->cum_zeit < limit) {
GPtrArray *list = g_ptr_array_new();
for (i = 0; i < refset->list1->len; ++i) {
g_ptr_array_add(list, g_ptr_array_index(refset->list1, i));
}
for (i = 0; i < refset->list2->len; ++i) {
g_ptr_array_add(list, g_ptr_array_index(refset->list2, i));
}
compute_fitness(scatter_search);
refset->newsol = 0;
if (scatter_search->iter > 0) {
int best = scatter_search->upperbound;
CCutil_suspend_timer(timer);
CCutil_resume_timer(timer);
double rel_error = ((double)best - (double)scatter_search->lowerbound) /
(double)scatter_search->lowerbound;
printf("iteration %d with best wct %d and rel error %f, number of new solutions %d, time = %f\n",
scatter_search->iter, best, rel_error, nbnew_sol, timer->cum_zeit);
}
nbnew_sol = 0;
k_subset_init(list->len, 2, totsubset, &flag);
while (flag && scatter_search->status != opt) {
solution *new_sol = CC_SAFE_MALLOC(1, solution);
solution_init(new_sol);
solution_alloc(new_sol, nmachines, nbjobs);
int rval = 1;
rval = combine_PM(scatter_search, list, totsubset, 2, new_sol);
if (!rval) {
solution_calc(new_sol, *(scatter_search->jobarray));
new_sol->iter = scatter_search->iter + 1;
localsearch_random_k(new_sol, scatter_search->lowerbound, 2);
solution_unique(new_sol);
if (!dynamic_update(scatter_search, list, new_sol)) {
if (new_sol->totalweightcomptime < scatter_search->upperbound) {
scatter_search->upperbound = new_sol->totalweightcomptime;
}
if (new_sol->totalweightcomptime == scatter_search->lowerbound) {
scatter_search->status = opt;
printf("Found optimal with SS with subset generation 1\n");
}
nbnew_sol++;
} else {
solution_free(new_sol);
CC_IFFREE(new_sol, solution);
}
} else {
solution_free(new_sol);
CC_IFFREE(new_sol, solution);
}
k_subset_lex_successor(list->len, 2, totsubset, &flag);
}
k_subset_init(list->len, 3, totsubset, &flag);
solution *sol = (solution *)NULL;
sol = (solution *) g_ptr_array_index(list, 0);
while (flag && scatter_search->status != opt) {
solution *new_sol = CC_SAFE_MALLOC(1, solution);
solution_init(new_sol);
solution_alloc(new_sol, nmachines, nbjobs);
int rval = 1;
rval = combine_PM(scatter_search, list, totsubset, 3,
new_sol); //Dell'Amico et al.
if (!rval) {
solution_calc(new_sol, *(scatter_search->jobarray));
new_sol->iter = scatter_search->iter + 1;
localsearch_random_k(new_sol, scatter_search->lowerbound, 2);
solution_unique(new_sol);
if (!dynamic_update(scatter_search, list, new_sol)) {
if (new_sol->totalweightcomptime < scatter_search->upperbound) {
scatter_search->upperbound = new_sol->totalweightcomptime;
}
if (new_sol->totalweightcomptime == scatter_search->lowerbound) {
scatter_search->status = opt;
printf("Found optimal with SS\n");
}
nbnew_sol++;
} else {
solution_free(new_sol);
CC_IFFREE(new_sol, solution);
}
} else {
solution_free(new_sol);
CC_IFFREE(new_sol, solution);
}
k_subset_lex_successor(list->len, 3, totsubset, &flag);
sol = (solution *) g_ptr_array_index(list, totsubset[1] - 1);
}
k_subset_init(list->len, 4, totsubset, &flag);
sol = (solution *) g_ptr_array_index(list, 0);
solution *temp_sol = (solution *) g_ptr_array_index(list, 1);
while (flag && scatter_search->status != opt
&& sol->totalweightcomptime <= scatter_search->upperbound
&& temp_sol->totalweightcomptime <= scatter_search->upperbound) {
solution *new_sol = CC_SAFE_MALLOC(1, solution);
solution_init(new_sol);
solution_alloc(new_sol, nmachines, nbjobs);
int rval = 1;
rval = combine_PM(scatter_search, list, totsubset, 4, new_sol);
if (!rval) {
solution_calc(new_sol, *(scatter_search->jobarray));
new_sol->iter = scatter_search->iter + 1;
localsearch_random_k(new_sol, scatter_search->lowerbound, 2);
solution_unique(new_sol);
if (!dynamic_update(scatter_search, list, new_sol)) {
if (new_sol->totalweightcomptime < scatter_search->upperbound) {
scatter_search->upperbound = new_sol->totalweightcomptime;
}
if (new_sol->totalweightcomptime == scatter_search->lowerbound) {
scatter_search->status = opt;
printf("Found optimal with SS\n");
}
nbnew_sol++;
} else {
solution_free(new_sol);
CC_IFFREE(new_sol, solution);
}
} else {
solution_free(new_sol);
CC_IFFREE(new_sol, solution);
}
k_subset_lex_successor(list->len, 4, totsubset, &flag);
sol = (solution *) g_ptr_array_index(list, totsubset[1] - 1);
temp_sol = (solution *)g_ptr_array_index(list, totsubset[2] - 1);
}
for (i = 0; i < refset->list2->len + 1; ++i) {
totsubset[i] = i;
}
for (i = 5; i < refset->list2->len + 1
&& scatter_search->status != opt; i++) {
solution *new_sol = CC_SAFE_MALLOC(1, solution);
solution_init(new_sol);
solution_alloc(new_sol, nmachines, nbjobs);
int rval = 1;
rval = combine_PM(scatter_search, list, totsubset, i, new_sol);
if (!rval) {
solution_calc(new_sol, *(scatter_search->jobarray));
new_sol->iter = scatter_search->iter + 1;
localsearch_random_k(new_sol, scatter_search->lowerbound, 2);
solution_unique(new_sol);
if (!dynamic_update(scatter_search, list, new_sol)) {
if (new_sol->totalweightcomptime < scatter_search->upperbound) {
scatter_search->upperbound = new_sol->totalweightcomptime;
}
if (new_sol->totalweightcomptime == scatter_search->lowerbound) {
scatter_search->status = opt;
printf("Found optimal with SS\n");
}
nbnew_sol++;
} else {
solution_free(new_sol);
CC_IFFREE(new_sol, solution);
}
} else {
solution_free(new_sol);
CC_IFFREE(new_sol, solution);
}
}
scatter_search->iter++;
if (nbnew_sol == 0) {
nb_noimprovements++;
}
if (refset->newsol == 0 && scatter_search->iter < 10
&& nb_noimprovements < 5) {
add_solution_refset(scatter_search);
refset->newsol = 1;
}
g_ptr_array_free(list, TRUE);
}
CLEAN:
CC_IFFREE(totsubset, int);
return val;
}
//--------------------------------------------------------------------
void start_steady_state_ga(int pop_size, int num_gens, int num_dims, int num_bits_per_dimension, double pcross, double pm, double min_x, double max_x)
// Steady-State genetic algorithm
// each step:
// pick 2 parents, mate them,
// mutate the offspring
// and replace the worst in the population
// (only if offspring are better)
{
// allocate memory
b_chromosome *population;
population = (b_chromosome*)malloc(pop_size * sizeof(b_chromosome));
for (int i = 0; i < pop_size; i++)
population[i].x = (char*)malloc(num_dims * num_bits_per_dimension);
b_chromosome offspring1, offspring2;
offspring1.x = (char*)malloc(num_dims * num_bits_per_dimension);
offspring2.x = (char*)malloc(num_dims * num_bits_per_dimension);
// initialize
for (int i = 0; i < pop_size; i++) {
generate_random(population[i], num_dims, num_bits_per_dimension);
compute_fitness(&population[i], num_dims, num_bits_per_dimension, min_x, max_x);
}
qsort((void *)population, pop_size, sizeof(population[0]), sort_function);
printf("generation 0\n");
// print the best from generation 0
print_chromosome(&population[0], num_dims, num_bits_per_dimension, min_x, max_x);
for (int g = 1; g < num_gens; g++) {
for (int k = 0; k < pop_size; k += 2) {
// choose the parents using binary tournament
int r1 = tournament_selection(2, population, pop_size);
int r2 = tournament_selection(2, population, pop_size);
// crossover
double p = rand() / double(RAND_MAX);
if (p < pcross)
one_cut_point_crossover(population[r1], population[r2], offspring1, offspring2, num_dims, num_bits_per_dimension);
else {
copy_individual(&offspring1, population[r1], num_dims, num_bits_per_dimension);
copy_individual(&offspring2, population[r2], num_dims, num_bits_per_dimension);
}
// mutate the result and compute its fitness
mutation(offspring1, num_dims, num_bits_per_dimension, pm);
compute_fitness(&offspring1, num_dims, num_bits_per_dimension, min_x, max_x);
mutation(offspring2, num_dims, num_bits_per_dimension, pm);
compute_fitness(&offspring2, num_dims, num_bits_per_dimension, min_x, max_x);
// are offspring better than the worst ?
if (offspring1.fitness < population[pop_size - 1].fitness) {
copy_individual(&population[pop_size - 1], offspring1, num_dims, num_bits_per_dimension);
qsort((void *)population, pop_size, sizeof(population[0]), sort_function);
}
if (offspring2.fitness < population[pop_size - 1].fitness) {
copy_individual(&population[pop_size - 1], offspring2, num_dims, num_bits_per_dimension);
qsort((void *)population, pop_size, sizeof(population[0]), sort_function);
}
}
printf("generation %d\n", g);
print_chromosome(&population[0], num_dims, num_bits_per_dimension, min_x, max_x);
}
// free memory
free(offspring1.x);
free(offspring2.x);
for (int i = 0; i < pop_size; i++)
free(population[i].x);
free(population);
}
bool RRSchedule::add_week()
// Add a full set of timeslots to the week
{
// Guarantee everyone played a sufficient number of times
bool mincheck = (min_per_night <= VectMin(this_week_played));
if (week0)
{
int temp_min_per_night = (max_courts * (max_times - skip_first) * 2) / max_teams;
mincheck = temp_min_per_night <= VectMin(this_week_played);
}
bool goodSort = false;
bool acceptableWait = false;
if (mincheck)
{
// Check to ensure sorting is acceptable?
goodSort = sort_times_new(timeslots);
if (goodSort)
{
Vector temp_team_waits = total_waiting_by_team;
VectDotSum(temp_team_waits, compute_team_waits_for_week(timeslots));
acceptableWait = ( VectMax(temp_team_waits) - VectMin(temp_team_waits) <= MAX_WAIT_GAP);
if (acceptableWait)
{
// Roll up timeslot information into the week and log
weeks.push_back(timeslots);
store_timeslot();
// No longer first week after successful addition of timeslot
week0 = false;
// Reset the timeslots and matchups for this week
allocate2D(timeslots, max_times, max_courts*2);
init2D(this_week_matchups, max_teams, max_teams);
total_this_week_played.push_back(this_week_played);
init1D(this_week_played,max_teams);
compute_total_team_waits();
compute_fitness();
// Note progress for user
printf ("Current Size: %d weeks (Max Weeks: %d). Total Wait Time: %d Fitness Level: %d (Scaled Fitness: %.2f) Printed Solutions: %d\n", int(weeks.size()), max_weeks, total_wait_time, fitness_level, scaled_fitness_level, PRINTED_SOLUTIONS);
std::cout << weeks.size() << std::endl;
if (weeks.size() == max_weeks)
{
printf("Full Solution?\n");
fullSolution = true;
}
else{
printf ("Not full Solution\n");
}
}
}
}
return mincheck and goodSort and acceptableWait;
}
