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 #include "canvas_cairo.h"
  24
  25 #include "xfig_tracer.h"
  26
  27 void generate_png(Universe *universe, scalar_t scale, FILE *file) {
  28   CanvasCairo canvas(scale, universe->width(), universe->height());
  29   universe->draw(&canvas);
  30   canvas.write_png(file);
  31 }
  32
  33 // To train
  34 // ./main --task hit_shape.task 0 --action-mode=random --nb-ticks=5000 --proportion-for-training=0.5 --save-file=dump.mem --no-window
  35
  36 // To test
  37 // ./main --task hit_shape.task 0 --action-mode=intelligent --load-file=dump.mem
  38
  39 //////////////////////////////////////////////////////////////////////
  40
  41 void check_opt(int argc, char **argv, int n_opt, int n, const char *help) {
  42   if(n_opt + n >= argc) {
  43     cerr << "Missing argument for " << argv[n_opt] << "." << endl;
  44     cerr << "Expecting " << help << "." << endl;
  45     exit(1);
  46   }
  47 }
  48
  49 void print_help_and_exit(int e) {
  50   cout << "Arguments:" << endl;
  51   cout << "  --no-window" << endl;
  52   cout << "  --nb-ticks=<int: number of ticks>" << endl;
  53   cout << "  --nb-training-iterations=<int: number of training iterations>" << endl;
  54   cout << "  --load-file=<filename: dump file>" << endl;
  55   cout << "  --save-file=<filename: dump file>" << endl;
  56   cout << "  --proportion-for-training=<float: proportion of samples for training>" << endl;
  57   cout << "  --action-mode=<idle|random|intelligent>" << endl;
  58   cout << "  --task <filename: task to load> <int: degree>" << endl;
  59   exit(e);
  60 }
  61
  62 //////////////////////////////////////////////////////////////////////
  63
  64 int main(int argc, char **argv) {
  65
  66   const int buffer_size = 256;
  67   char intelligence_load_file[buffer_size] = "", intelligence_save_file[buffer_size] = "";
  68
  69   Task *task = 0;
  70   int task_degree = 0;
  71
  72   int nb_ticks = 10000;
  73   int nb_training_iterations = 10;
  74   scalar_t proportion_for_training = -1;
  75
  76   Polygon *grabbed_polygon = 0;
  77   scalar_t relative_grab_x = 0, relative_grab_y = 0;
  78
  79   bool quit = false;
  80   bool press_shift = false;
  81   enum { IDLE, RANDOM, INTELLIGENT } action_mode = IDLE;
  82   bool got_event = true;
  83   int current_action = 0;
  84
  85   scalar_t last_hand_x = 0, last_hand_y = 0;
  86   Polygon *last_grabbing = 0;
  87   bool no_window = false;
  88
  89   //////////////////////////////////////////////////////////////////////
  90   //                    Parsing the shell arguments
  91   //////////////////////////////////////////////////////////////////////
  92
  93   int i = 1;
  94   while(i < argc) {
  95     if(argc == 1 || strcmp(argv[i], "--help") == 0) print_help_and_exit(0);
  96
  97     else if(strcmp(argv[i], "--test") == 0) {
  98       test_approximer();
  99       exit(0);
 100     }
 101
 102     else if(strcmp(argv[i], "--task") == 0) {
 103       check_opt(argc, argv, i, 2, "<filename: task to load> <int: degree>");
 104       if(task) {
 105         cerr << "Can not load two tasks." << endl;
 106         exit(1);
 107       }
 108       task = load_task(argv[i+1]);
 109       task_degree = atoi(argv[i+2]);
 110       i += 3;
 111
 112     } else if(strncmp(argv[i], "--", 2) == 0) {
 113       char variable_name[buffer_size] = "", variable_value[buffer_size] = "";
 114       char *o = argv[i]+2, *s = variable_name, *u = variable_value;
 115       while(*o && *o != '=') *s++ = *o++;
 116       if(*o) {
 117         o++;
 118         while(*o) *u++ = *o++;
 119       }
 120
 121       if(strcmp(variable_name, "nb-ticks") == 0)
 122         nb_ticks = atoi(variable_value);
 123       else if(strcmp(variable_name, "nb-training-iterations") == 0)
 124         nb_training_iterations = atoi(variable_value);
 125       else if(strcmp(variable_name, "proportion-for-training") == 0)
 126         proportion_for_training = atof(variable_value);
 127       else if(strcmp(variable_name, "no-window") == 0)
 128         no_window = true;
 129       else if(strcmp(variable_name, "save-file") == 0)
 130         strcpy(intelligence_save_file, variable_value);
 131       else if(strcmp(variable_name, "load-file") == 0)
 132         strcpy(intelligence_load_file, variable_value);
 133       else if(strcmp(variable_name, "action-mode") == 0) {
 134         if(strcmp(variable_value, "idle") == 0) action_mode = IDLE;
 135         else if(strcmp(variable_value, "random") == 0) action_mode = RANDOM;
 136         else if(strcmp(variable_value, "intelligent") == 0) action_mode = INTELLIGENT;
 137         else {
 138           cerr << "The only known modes are idle, random and intelligent" << endl;
 139           exit(1);
 140         }
 141       } else {
 142         cerr << "Unknown option " << argv[i] << endl;
 143         print_help_and_exit(1);
 144       }
 145       i++;
 146     } else {
 147       cerr << "Unknown option " << argv[i] << endl;
 148       print_help_and_exit(1);
 149     }
 150   }
 151
 152   cout << "FlatLand, a toy universe for goal-planning experiments." << endl;
 153
 154   if(!task) {
 155     task = load_task("dummy.so");
 156     task_degree = 0;
 157   }
 158
 159   cout << "Loaded task " << task->name()
 160        << " with degree " << task_degree << "/" << task->nb_degrees()
 161        << endl;
 162
 163   if(task_degree < 0 || task_degree >= task->nb_degrees()) {
 164     cout << "Invalid degree: " << task_degree << "." << endl;
 165     exit(1);
 166   }
 167
 168   //////////////////////////////////////////////////////////////////////
 169   //                      Various initializations
 170   //////////////////////////////////////////////////////////////////////
 171
 172   Universe universe(100, task->width(), task->height());
 173   task->init(&universe, task_degree);
 174   Retina retina(&universe);
 175   Manipulator manipulator(task);
 176   manipulator.force_move(task->width()/2, task->height()/2);
 177   retina.set_location(manipulator.hand_x(), manipulator.hand_y());
 178
 179   SimpleWindow *window_main = 0, *window_brain = 0;
 180   int window_main_fd = -1;
 181
 182 #ifdef CAIRO_SUPPORT
 183   // cairo_t *window_main_cairo_cr = 0;
 184 #endif
 185
 186   MapConcatener sensory_map(2);
 187   sensory_map.add_map(&retina);
 188   sensory_map.add_map(&manipulator);
 189   sensory_map.init();
 190
 191   MapExpander expanded_map(1000);
 192   expanded_map.set_input(&sensory_map);
 193   expanded_map.init();
 194
 195   Intelligence intelligence(&expanded_map, &manipulator, nb_ticks + 1, nb_training_iterations);
 196   intelligence.update(0, 0.0);
 197
 198   if(intelligence_load_file[0]) {
 199     cout << "Loading from " << intelligence_load_file << " ... " ;
 200     cout.flush();
 201     ifstream in(intelligence_load_file);
 202     if(in.fail()) {
 203       cerr << "error reading " << intelligence_load_file << "." << endl;
 204       exit(1);
 205     }
 206     intelligence.load(in);
 207     cout << "done." << endl ;
 208   }
 209
 210   if(no_window) {
 211     cout << "Started without windows." << endl;
 212   } else {
 213     window_main = new SimpleWindow("Universe (main window)", 4, 4, task->width(), task->height());
 214     window_main_fd = window_main->file_descriptor();
 215     window_main->map();
 216 #ifdef CAIRO_SUPPORT
 217     // window_main_cairo_cr = window_main->get_cairo_context_resource();
 218 #endif
 219     cout << "When the main window has the focus, press `q' to quit and click and drag to move" << endl
 220          << "objects." << endl;
 221     window_brain = new SimpleWindow("Universe (brain)",
 222                                     12 + task->width(), 4,
 223                                     retina.width(), retina.height() + manipulator.parameter_height());
 224     window_brain->map();
 225   }
 226
 227   int tick = 0;
 228   time_t last_t = 0;
 229   scalar_t sum_reward = 0;
 230
 231   //////////////////////////////////////////////////////////////////////
 232   //                         The main loop
 233   //////////////////////////////////////////////////////////////////////
 234
 235   while(!quit && tick != nb_ticks) {
 236
 237     int r;
 238     fd_set fds;
 239
 240
 241     if(window_main) {
 242       struct timeval tv;
 243       FD_ZERO (&fds);
 244       FD_SET (window_main_fd, &fds);
 245       tv.tv_sec = 0;
 246       tv.tv_usec = 5000; // 0.05s
 247       r = select(window_main_fd + 1, &fds, 0, 0, &tv);
 248     } else r = 0;
 249
 250     time_t t = time(0);
 251
 252     if(t > last_t) {
 253       last_t = t;
 254       cout << tick << " " << sum_reward << "              \r"; cout.flush();
 255     }
 256
 257     if(r == 0) { // No window event, thus it's the clock tick
 258
 259         int nb_it = 10;
 260
 261         bool changed = got_event;
 262         got_event = false;
 263
 264         switch(action_mode) {
 265         case IDLE:
 266           break;
 267         case RANDOM:
 268           current_action = manipulator.random_action();
 269           break;
 270         case INTELLIGENT:
 271           current_action = intelligence.best_action();
 272           //           if(drand48() < 0.5) current_action = intelligence.best_action();
 273           //           else                current_action = manipulator.random_action();
 274           break;
 275         }
 276
 277         manipulator.do_action(current_action);
 278
 279         scalar_t dt = 1.0/scalar_t(nb_it);
 280         for(int k = 0; k < nb_it; k++) {
 281           manipulator.update(dt, &universe);
 282           task->update(dt, &universe, &manipulator);
 283           changed |= universe.update(dt);
 284         }
 285
 286         tick++;
 287
 288         changed |= manipulator.hand_x() != last_hand_x ||
 289           manipulator.hand_y() != last_hand_y ||
 290           manipulator.grabbing() != last_grabbing;
 291
 292         scalar_t reward = task->reward(&universe, &manipulator);
 293         sum_reward += abs(reward);
 294         intelligence.update(current_action, reward);
 295         expanded_map.update_map();
 296
 297         if(changed) {
 298           last_hand_x = manipulator.hand_x();
 299           last_hand_y = manipulator.hand_y();
 300           last_grabbing = manipulator.grabbing();
 301
 302           retina.set_location(manipulator.hand_x(),
 303                               manipulator.hand_y());
 304
 305           if(window_main) {
 306             window_main->color(0.0, 0.0, 0.0);
 307             window_main->color(1.0, 1.0, 1.0);
 308             window_main->fill();
 309
 310 // #ifdef CAIRO_SUPPORT
 311             // CanvasCairo cc;
 312             // cc._context_resource = window_main_cairo_cr;
 313             // universe.draw(&cc);
 314 // #else
 315             universe.draw(window_main);
 316 // #endif
 317
 318             task->draw(window_main);
 319             manipulator.draw_on_universe(window_main);
 320             retina.draw_on_universe(window_main);
 321
 322             if(grabbed_polygon) {
 323               int x, y, delta = 3;
 324               x = int(grabbed_polygon->absolute_x(relative_grab_x, relative_grab_y));
 325               y = int(grabbed_polygon->absolute_y(relative_grab_x, relative_grab_y));
 326               window_main->color(0.0, 0.0, 0.0);
 327               window_main->draw_line(x - delta, y, x + delta, y);
 328               window_main->draw_line(x, y - delta, x, y + delta);
 329             }
 330
 331             window_main->show();
 332
 333             if(window_brain) {
 334               retina.draw_parameters(0, 0, window_brain);
 335               manipulator.draw_parameters(0, retina.height() + 1, window_brain);
 336               window_brain->show();
 337             }
 338           }
 339         }
 340
 341     } else if(r > 0) { // We got window events, let's process them
 342
 343       got_event = true;
 344
 345       if(FD_ISSET(window_main_fd, &fds)) {
 346
 347         SimpleEvent se;
 348
 349         do {
 350           se = window_main->event();
 351
 352           switch(se.type) {
 353
 354           case SimpleEvent::MOUSE_CLICK_PRESS:
 355             {
 356               switch(se.button) {
 357
 358               case 1:
 359                 if(press_shift) {
 360                   manipulator.force_move(se.x, se.y);
 361                   manipulator.do_action(Manipulator::ACTION_GRAB);
 362                 } else {
 363                   grabbed_polygon = universe.pick_polygon(se.x, se.y);
 364                   if(grabbed_polygon) {
 365                     relative_grab_x = grabbed_polygon->relative_x(se.x, se.y);
 366                     relative_grab_y = grabbed_polygon->relative_y(se.x, se.y);
 367                   }
 368                 }
 369                 break;
 370               case 4:
 371                 {
 372                   Polygon *g = universe.pick_polygon(se.x, se.y);
 373                   if(g) g->_theta += M_PI/32;
 374                 }
 375                 break;
 376               case 5:
 377                 {
 378                   Polygon *g = universe.pick_polygon(se.x, se.y);
 379                   if(g) g->_theta -= M_PI/32;
 380                 }
 381                 break;
 382               }
 383             }
 384             break;
 385
 386           case SimpleEvent::MOUSE_CLICK_RELEASE:
 387             switch(se.button) {
 388             case 1:
 389               if(press_shift) manipulator.do_action(Manipulator::ACTION_RELEASE);
 390               else            grabbed_polygon = 0;
 391               break;
 392             default:
 393               break;
 394             }
 395
 396           case SimpleEvent::MOUSE_MOTION:
 397             {
 398               if(press_shift) {
 399                 manipulator.force_move(se.x, se.y);
 400               } else if(grabbed_polygon) {
 401                 scalar_t xf, yf, force_x, force_y, f, fmax = 100;
 402                 xf = grabbed_polygon->absolute_x(relative_grab_x, relative_grab_y);
 403                 yf = grabbed_polygon->absolute_y(relative_grab_x, relative_grab_y);
 404                 force_x = se.x - xf;
 405                 force_y = se.y - yf;
 406                 f = sqrt(sq(force_x) + sq(force_y));
 407                 if(f > fmax) { force_x = (force_x * fmax)/f; force_y = (force_y * fmax)/f; }
 408                 grabbed_polygon->apply_force(0.1, xf, yf, force_x, force_y);
 409               }
 410               break;
 411             }
 412             break;
 413
 414           case SimpleEvent::KEY_PRESS:
 415             {
 416               if(strcmp(se.key, "q") == 0) {
 417                 quit = true;
 418               }
 419
 420               else if(strcmp(se.key, "s") == 0) {
 421
 422                 retina.save_as_ppm("/tmp/retina.ppm");
 423                 cout << "Retina screen shot saved in /tmp/retina.ppm" << endl;
 424
 425                 {
 426                   XFigTracer tracer("/tmp/universe.fig");
 427                   universe.print_xfig(&tracer);
 428                 }
 429
 430 #ifdef CAIRO_SUPPORT
 431                 {
 432                   FILE *file = fopen("/tmp/universe.png", "w");
 433                   generate_png(&universe, 0.25, file);
 434                   // generate_png(task->width(), task->height(), &universe, "/tmp/universe.png");
 435                   cout << "Universe image saved in /tmp/universe.png" << endl;
 436                 }
 437 #endif
 438
 439               }
 440
 441               else if(strcmp(se.key, "Shift_L") == 0 || strcmp(se.key, "Shift_R") == 0) {
 442                 press_shift = true;
 443               }
 444
 445               else if(strcmp(se.key, "Up") == 0) {
 446                 manipulator.do_action(Manipulator::ACTION_MOVE_UP);
 447               }
 448
 449               else if(strcmp(se.key, "Right") == 0) {
 450                 manipulator.do_action(Manipulator::ACTION_MOVE_RIGHT);
 451               }
 452
 453               else if(strcmp(se.key, "Down") == 0) {
 454                 manipulator.do_action(Manipulator::ACTION_MOVE_DOWN);
 455               }
 456
 457               else if(strcmp(se.key, "Left") == 0) {
 458                 manipulator.do_action(Manipulator::ACTION_MOVE_LEFT);
 459               }
 460
 461               else if(strcmp(se.key, "g") == 0) {
 462                 manipulator.do_action(Manipulator::ACTION_GRAB);
 463               }
 464
 465               else if(strcmp(se.key, "r") == 0) {
 466                 manipulator.do_action(Manipulator::ACTION_RELEASE);
 467               }
 468
 469               else if(strcmp(se.key, "space") == 0) {
 470                 switch(action_mode) {
 471                 case IDLE:
 472                   action_mode = RANDOM;
 473                   cout << "Switched to random mode" << endl;
 474                   break;
 475                 case RANDOM:
 476                   action_mode = INTELLIGENT;
 477                   cout << "Switched to intelligent mode" << endl;
 478                   break;
 479                 case INTELLIGENT:
 480                   cout << "Switched to idle mode" << endl;
 481                   action_mode = IDLE;
 482                   break;
 483                 }
 484               }
 485
 486               else cout << "Undefined key " << se.key << endl;
 487             }
 488             break;
 489
 490           case SimpleEvent::KEY_RELEASE:
 491             {
 492               if(strcmp(se.key, "Shift_L") == 0 || strcmp(se.key, "Shift_R") == 0) press_shift = false;
 493             }
 494             break;
 495
 496           default:
 497             break;
 498
 499           }
 500         } while(se.type != SimpleEvent::NO_EVENT);
 501       } else {
 502         cerr << "Error on select: " << strerror(errno) << endl;
 503         exit(1);
 504       }
 505     }
 506   }
 507
 508   if(proportion_for_training > 0) {
 509     cout << "Learning ... "; cout.flush();
 510     intelligence.learn(proportion_for_training);
 511     cout << "done." << endl;
 512   }
 513
 514   if(intelligence_save_file[0]) {
 515     cout << "Saving to " << intelligence_save_file << endl; cout.flush();
 516     ofstream os(intelligence_save_file);
 517     if(os.fail()) {
 518       cerr << "error writing " << intelligence_save_file << "." << endl;
 519       exit(1);
 520     }
 521     cout << "done." << endl;
 522     intelligence.save(os);
 523   }
 524
 525   delete window_brain;
 526   delete window_main;
 527
 528 }