main.cc

   1
   2 // Written and (C) by Francois Fleuret
   3 // Contact <francois.fleuret@idiap.ch> for comments & bug reports
   4
   5 #include <iostream>
   6 #include <fstream>
   7 #include <cmath>
   8 #include <stdio.h>
   9 #include <stdlib.h>
  10 #include <stdint.h>
  11 #include <errno.h>
  12 #include <string.h>
  13
  14 using namespace std;
  15
  16 #include "misc.h"
  17 #include "task.h"
  18 #include "simple_window.h"
  19 #include "universe.h"
  20 #include "retina.h"
  21 #include "manipulator.h"
  22 #include "intelligence.h"
  23
  24 // To train
  25 // ./main --task hit_shape.task 0 --action-mode=random --nb-ticks=5000 --proportion-for-training=0.5 --save-file=dump.mem --no-window
  26
  27 // To test
  28 // ./main --task hit_shape.task 0 --action-mode=intelligent --load-file=dump.mem
  29
  30 //////////////////////////////////////////////////////////////////////
  31
  32 void check_opt(int argc, char **argv, int n_opt, int n, const char *help) {
  33   if(n_opt + n >= argc) {
  34     cerr << "Missing argument for " << argv[n_opt] << "." << endl;
  35     cerr << "Expecting " << help << "." << endl;
  36     exit(1);
  37   }
  38 }
  39
  40 void print_help_and_exit(int e) {
  41   cout << "Arguments:" << endl;
  42   cout << "  --no-window" << endl;
  43   cout << "  --nb-ticks=<int: number of ticks>" << endl;
  44   cout << "  --nb-training-iterations=<int: number of training iterations>" << endl;
  45   cout << "  --load-file=<filename: dump file>" << endl;
  46   cout << "  --save-file=<filename: dump file>" << endl;
  47   cout << "  --proportion-for-training=<float: proportion of samples for training>" << endl;
  48   cout << "  --action-mode=<idle|random|intelligent>" << endl;
  49   cout << "  --task <filename: task to load> <int: degree>" << endl;
  50   exit(e);
  51 }
  52
  53 //////////////////////////////////////////////////////////////////////
  54
  55 int main(int argc, char **argv) {
  56
  57   const int buffer_size = 256;
  58   char intelligence_load_file[buffer_size] = "", intelligence_save_file[buffer_size] = "";
  59
  60   Task *task = 0;
  61   int task_degree = 0;
  62
  63   int nb_ticks = 10000;
  64   int nb_training_iterations = 10;
  65   scalar_t proportion_for_training = -1;
  66
  67   Polygon *grabbed_polygon = 0;
  68   scalar_t relative_grab_x = 0, relative_grab_y = 0;
  69
  70   bool quit = false;
  71   bool press_shift = false;
  72   enum { IDLE, RANDOM, INTELLIGENT } action_mode = IDLE;
  73   bool got_event = true;
  74   int current_action = 0;
  75
  76   scalar_t last_hand_x = 0, last_hand_y = 0;
  77   Polygon *last_grabbing = 0;
  78   bool no_window = false;
  79
  80   //////////////////////////////////////////////////////////////////////
  81   //                    Parsing the shell arguments
  82   //////////////////////////////////////////////////////////////////////
  83
  84   int i = 1;
  85   while(i < argc) {
  86     if(argc == 1 || strcmp(argv[i], "--help") == 0) print_help_and_exit(0);
  87
  88     else if(strcmp(argv[i], "--test") == 0) {
  89       test_approximer();
  90       exit(0);
  91     }
  92
  93     else if(strcmp(argv[i], "--task") == 0) {
  94       check_opt(argc, argv, i, 2, "<filename: task to load> <int: degree>");
  95       if(task) {
  96         cerr << "Can not load two tasks." << endl;
  97         exit(1);
  98       }
  99       task = load_task(argv[i+1]);
 100       task_degree = atoi(argv[i+2]);
 101       i += 3;
 102
 103     } else if(strncmp(argv[i], "--", 2) == 0) {
 104       char variable_name[buffer_size] = "", variable_value[buffer_size] = "";
 105       char *o = argv[i]+2, *s = variable_name, *u = variable_value;
 106       while(*o && *o != '=') *s++ = *o++;
 107       if(*o) {
 108         o++;
 109         while(*o) *u++ = *o++;
 110       }
 111
 112       if(strcmp(variable_name, "nb-ticks") == 0)
 113         nb_ticks = atoi(variable_value);
 114       else if(strcmp(variable_name, "nb-training-iterations") == 0)
 115         nb_training_iterations = atoi(variable_value);
 116       else if(strcmp(variable_name, "proportion-for-training") == 0)
 117         proportion_for_training = atof(variable_value);
 118       else if(strcmp(variable_name, "no-window") == 0)
 119         no_window = true;
 120       else if(strcmp(variable_name, "save-file") == 0)
 121         strcpy(intelligence_save_file, variable_value);
 122       else if(strcmp(variable_name, "load-file") == 0)
 123         strcpy(intelligence_load_file, variable_value);
 124       else if(strcmp(variable_name, "action-mode") == 0) {
 125         if(strcmp(variable_value, "idle") == 0) action_mode = IDLE;
 126         else if(strcmp(variable_value, "random") == 0) action_mode = RANDOM;
 127         else if(strcmp(variable_value, "intelligent") == 0) action_mode = INTELLIGENT;
 128         else {
 129           cerr << "The only known modes are idle, random and intelligent" << endl;
 130           exit(1);
 131         }
 132       } else {
 133         cerr << "Unknown option " << argv[i] << endl;
 134         print_help_and_exit(1);
 135       }
 136       i++;
 137     } else {
 138       cerr << "Unknown option " << argv[i] << endl;
 139       print_help_and_exit(1);
 140     }
 141   }
 142
 143   cout << "FlatLand, a toy universe for goal-planning experiments." << endl;
 144   cout << "$Id: main.cc,v 1.89 2007-06-16 13:51:53 fleuret Exp $" << endl;
 145
 146   if(!task) {
 147     task = load_task("dummy.task");
 148     task_degree = 0;
 149   }
 150
 151   cout << "Loaded task " << task->name()
 152        << " with degree " << task_degree << "/" << task->nb_degrees()
 153        << endl;
 154
 155   if(task_degree < 0 || task_degree >= task->nb_degrees()) {
 156     cout << "Invalid degree: " << task_degree << "." << endl;
 157     exit(1);
 158   }
 159
 160   //////////////////////////////////////////////////////////////////////
 161   //                      Various initializations
 162   //////////////////////////////////////////////////////////////////////
 163
 164   Universe universe(100, task->width(), task->height());
 165   task->init(&universe, task_degree);
 166   Retina retina(&universe);
 167   Manipulator manipulator(task);
 168   manipulator.force_move(task->width()/2, task->height()/2);
 169   retina.set_location(manipulator.hand_x(), manipulator.hand_y());
 170
 171   SimpleWindow *window_main = 0, *window_brain = 0;
 172
 173   int winfd = -1;
 174
 175   MapConcatener sensory_map(2);
 176   sensory_map.add_map(&retina);
 177   sensory_map.add_map(&manipulator);
 178   sensory_map.init();
 179
 180   MapExpander expanded_map(1000);
 181   expanded_map.set_input(&sensory_map);
 182   expanded_map.init();
 183
 184   Intelligence intelligence(&expanded_map, &manipulator, nb_ticks + 1, nb_training_iterations);
 185   intelligence.update(0, 0.0);
 186
 187   if(intelligence_load_file[0]) {
 188     cout << "Loading from " << intelligence_load_file << " ... " ;
 189     cout.flush();
 190     ifstream in(intelligence_load_file);
 191     if(in.fail()) {
 192       cerr << "error reading " << intelligence_load_file << "." << endl;
 193       exit(1);
 194     }
 195     intelligence.load(in);
 196     cout << "done." << endl ;
 197   }
 198
 199   if(!no_window) {
 200     window_main = new SimpleWindow("Universe (main window)", 4, 4, task->width(), task->height());
 201     winfd = window_main->file_descriptor();
 202     window_main->map();
 203     cout << "When the main window has the focus, press `q' to quit and click and drag to move" << endl
 204          << "objects." << endl;
 205     window_brain = new SimpleWindow("Universe (brain)",
 206                                      12 + task->width(), 4,
 207                                      retina.width(), retina.height() + manipulator.parameter_height());
 208     window_brain->map();
 209   } else {
 210     cout << "Started without windows." << endl;
 211   }
 212
 213   int tick = 0;
 214   time_t last_t = 0;
 215   scalar_t sum_reward = 0;
 216
 217   //////////////////////////////////////////////////////////////////////
 218   //                         The main loop
 219   //////////////////////////////////////////////////////////////////////
 220
 221   while(!quit && tick != nb_ticks) {
 222
 223     int r;
 224     fd_set fds;
 225
 226
 227     if(window_main) {
 228       struct timeval tv;
 229       FD_ZERO (&fds);
 230       FD_SET (winfd, &fds);
 231       tv.tv_sec = 0;
 232       tv.tv_usec = 5000; // 0.05s
 233       r = select(winfd + 1, &fds, 0, 0, &tv);
 234     } else r = 0;
 235
 236     time_t t = time(0);
 237
 238     if(t > last_t) {
 239       last_t = t;
 240       cout << tick << " " << sum_reward << "              \r"; cout.flush();
 241     }
 242
 243     if(r == 0) { // No window event, thus it's the clock tick
 244
 245         int nb_it = 10;
 246
 247         bool changed = got_event;
 248         got_event = false;
 249
 250         switch(action_mode) {
 251         case IDLE:
 252           break;
 253         case RANDOM:
 254           current_action = manipulator.random_action();
 255           break;
 256         case INTELLIGENT:
 257           current_action = intelligence.best_action();
 258           //           if(drand48() < 0.5) current_action = intelligence.best_action();
 259           //           else                current_action = manipulator.random_action();
 260           break;
 261         }
 262
 263         manipulator.do_action(current_action);
 264
 265         scalar_t dt = 1.0/scalar_t(nb_it);
 266         for(int k = 0; k < nb_it; k++) {
 267           manipulator.update(dt, &universe);
 268           task->update(dt, &universe, &manipulator);
 269           changed |= universe.update(dt);
 270         }
 271
 272         tick++;
 273
 274         changed |= manipulator.hand_x() != last_hand_x ||
 275           manipulator.hand_y() != last_hand_y ||
 276           manipulator.grabbing() != last_grabbing;
 277
 278         scalar_t reward = task->reward(&universe, &manipulator);
 279         sum_reward += abs(reward);
 280         intelligence.update(current_action, reward);
 281         expanded_map.update_map();
 282
 283         if(changed) {
 284           last_hand_x = manipulator.hand_x();
 285           last_hand_y = manipulator.hand_y();
 286           last_grabbing = manipulator.grabbing();
 287           retina.set_location(manipulator.hand_x(), manipulator.hand_y());
 288
 289           if(window_main) {
 290             window_main->color(0.0, 0.0, 0.0);
 291             window_main->fill();
 292             task->draw(window_main);
 293             universe.draw(window_main);
 294             manipulator.draw_on_universe(window_main);
 295             retina.draw_on_universe(window_main);
 296
 297             if(grabbed_polygon) {
 298               int x, y, delta = 3;
 299               x = int(grabbed_polygon->absolute_x(relative_grab_x, relative_grab_y));
 300               y = int(grabbed_polygon->absolute_y(relative_grab_x, relative_grab_y));
 301               window_main->color(0.0, 0.0, 0.0);
 302               window_main->draw_line(x - delta, y, x + delta, y);
 303               window_main->draw_line(x, y - delta, x, y + delta);
 304             }
 305
 306             window_main->show();
 307
 308             if(window_brain) {
 309               retina.draw_parameters(0, 0, window_brain);
 310               manipulator.draw_parameters(0, retina.height() + 1, window_brain);
 311               window_brain->show();
 312             }
 313           }
 314         }
 315
 316     } else if(r > 0) { // We got window events, let's process them
 317
 318       got_event = true;
 319
 320       if(FD_ISSET(winfd, &fds)) {
 321
 322         SimpleEvent se;
 323
 324         do {
 325           se = window_main->event();
 326
 327           switch(se.type) {
 328
 329           case SimpleEvent::MOUSE_CLICK_PRESS:
 330             {
 331               switch(se.button) {
 332
 333               case 1:
 334                 if(press_shift) {
 335                   manipulator.force_move(se.x, se.y);
 336                   manipulator.do_action(Manipulator::ACTION_GRAB);
 337                 } else {
 338                   grabbed_polygon = universe.pick_polygon(se.x, se.y);
 339                   if(grabbed_polygon) {
 340                     relative_grab_x = grabbed_polygon->relative_x(se.x, se.y);
 341                     relative_grab_y = grabbed_polygon->relative_y(se.x, se.y);
 342                   }
 343                 }
 344                 break;
 345               case 4:
 346                 {
 347                   Polygon *g = universe.pick_polygon(se.x, se.y);
 348                   if(g) g->_theta += M_PI/32;
 349                 }
 350                 break;
 351               case 5:
 352                 {
 353                   Polygon *g = universe.pick_polygon(se.x, se.y);
 354                   if(g) g->_theta -= M_PI/32;
 355                 }
 356                 break;
 357               }
 358             }
 359             break;
 360
 361           case SimpleEvent::MOUSE_CLICK_RELEASE:
 362             switch(se.button) {
 363             case 1:
 364               if(press_shift) manipulator.do_action(Manipulator::ACTION_RELEASE);
 365               else            grabbed_polygon = 0;
 366               break;
 367             default:
 368               break;
 369             }
 370
 371           case SimpleEvent::MOUSE_MOTION:
 372             {
 373               if(press_shift) manipulator.force_move(se.x, se.y);
 374               else {
 375                 if(grabbed_polygon) {
 376                   scalar_t xf, yf, force_x, force_y, f, fmax = 100;
 377                   xf = grabbed_polygon->absolute_x(relative_grab_x, relative_grab_y);
 378                   yf = grabbed_polygon->absolute_y(relative_grab_x, relative_grab_y);
 379                   force_x = se.x - xf;
 380                   force_y = se.y - yf;
 381                   f = sqrt(sq(force_x) + sq(force_y));
 382                   if(f > fmax) { force_x = (force_x * fmax)/f; force_y = (force_y * fmax)/f; }
 383                   grabbed_polygon->apply_force(0.1, xf, yf, force_x, force_y);
 384                 }
 385               }
 386               break;
 387             }
 388             break;
 389
 390           case SimpleEvent::KEY_PRESS:
 391             {
 392               if(strcmp(se.key, "q") == 0) quit = true;
 393               else if(strcmp(se.key, "s") == 0) {
 394                 retina.save_as_ppm("/tmp/retina.ppm");
 395                 cout << "Retina screen shot saved in /tmp/retina.ppm" << endl;
 396                 {
 397                   ofstream out("/tmp/universe.fig");
 398                   universe.print_fig(out);
 399                 }
 400               }
 401               else if(strcmp(se.key, "Shift_L") == 0 || strcmp(se.key, "Shift_R") == 0) press_shift = true;
 402
 403               else if(strcmp(se.key, "Up") == 0) manipulator.do_action(Manipulator::ACTION_MOVE_UP);
 404               else if(strcmp(se.key, "Right") == 0) manipulator.do_action(Manipulator::ACTION_MOVE_RIGHT);
 405               else if(strcmp(se.key, "Down") == 0) manipulator.do_action(Manipulator::ACTION_MOVE_DOWN);
 406               else if(strcmp(se.key, "Left") == 0) manipulator.do_action(Manipulator::ACTION_MOVE_LEFT);
 407               else if(strcmp(se.key, "g") == 0) manipulator.do_action(Manipulator::ACTION_GRAB);
 408               else if(strcmp(se.key, "r") == 0) manipulator.do_action(Manipulator::ACTION_RELEASE);
 409
 410               else if(strcmp(se.key, "space") == 0) {
 411                 switch(action_mode) {
 412                 case IDLE:
 413                   action_mode = RANDOM;
 414                   cout << "Switched to random mode" << endl;
 415                   break;
 416                 case RANDOM:
 417                   action_mode = INTELLIGENT;
 418                   cout << "Switched to intelligent mode" << endl;
 419                   break;
 420                 case INTELLIGENT:
 421                   cout << "Switched to idle mode" << endl;
 422                   action_mode = IDLE;
 423                   break;
 424                 }
 425               }
 426
 427               else cout << "Undefined key " << se.key << endl;
 428             }
 429             break;
 430
 431           case SimpleEvent::KEY_RELEASE:
 432             {
 433               if(strcmp(se.key, "Shift_L") == 0 || strcmp(se.key, "Shift_R") == 0) press_shift = false;
 434             }
 435             break;
 436
 437           default:
 438             break;
 439
 440           }
 441         } while(se.type != SimpleEvent::NO_EVENT);
 442       } else {
 443         cerr << "Error on select: " << strerror(errno) << endl;
 444         exit(1);
 445       }
 446     }
 447   }
 448
 449   if(proportion_for_training > 0) {
 450     cout << "Learning ... "; cout.flush();
 451     intelligence.learn(proportion_for_training);
 452     cout << "done." << endl;
 453   }
 454
 455   if(intelligence_save_file[0]) {
 456     cout << "Saving to " << intelligence_save_file << endl; cout.flush();
 457     ofstream os(intelligence_save_file);
 458     if(os.fail()) {
 459       cerr << "error writing " << intelligence_save_file << "." << endl;
 460       exit(1);
 461     }
 462     cout << "done." << endl;
 463     intelligence.save(os);
 464   }
 465
 466   delete window_brain;
 467   delete window_main;
 468
 469 }