main.cc

   1
   2 ////////////////////////////////////////////////////////////////////////////////
   3 // This program is free software; you can redistribute it and/or              //
   4 // modify it under the terms of the GNU General Public License                //
   5 // version 2 as published by the Free Software Foundation.                    //
   6 //                                                                            //
   7 // This program is distributed in the hope that it will be useful, but        //
   8 // WITHOUT ANY WARRANTY; without even the implied warranty of                 //
   9 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU          //
  10 // General Public License for more details.                                   //
  11 //                                                                            //
  12 // Written and (C) by François Fleuret                                        //
  13 // Contact <francois.fleuret@epfl.ch> for comments & bug reports              //
  14 ////////////////////////////////////////////////////////////////////////////////
  15
  16 #include <iostream>
  17 #include <fstream>
  18 #include <cmath>
  19 #include <stdio.h>
  20 #include <stdlib.h>
  21 #include <stdint.h>
  22 #include <errno.h>
  23 #include <string.h>
  24
  25 using namespace std;
  26
  27 #include "misc.h"
  28 #include "task.h"
  29 #include "simple_window.h"
  30 #include "universe.h"
  31 #include "retina.h"
  32 #include "manipulator.h"
  33 #include "intelligence.h"
  34
  35 // To train
  36 // ./main --task hit_shape.task 0 --action-mode=random --nb-ticks=5000 --proportion-for-training=0.5 --save-file=dump.mem --no-window
  37
  38 // To test
  39 // ./main --task hit_shape.task 0 --action-mode=intelligent --load-file=dump.mem
  40
  41 //////////////////////////////////////////////////////////////////////
  42
  43 void check_opt(int argc, char **argv, int n_opt, int n, char *help) {
  44   if(n_opt + n >= argc) {
  45     cerr << "Missing argument for " << argv[n_opt] << "." << endl;
  46     cerr << "Expecting " << help << "." << endl;
  47     exit(1);
  48   }
  49 }
  50
  51 void print_help_and_exit(int e) {
  52   cout << "Arguments:" << endl;
  53   cout << "  --no-window" << endl;
  54   cout << "  --nb-ticks=<int: number of ticks>" << endl;
  55   cout << "  --nb-training-iterations=<int: number of training iterations>" << endl;
  56   cout << "  --load-file=<filename: dump file>" << endl;
  57   cout << "  --save-file=<filename: dump file>" << endl;
  58   cout << "  --proportion-for-training=<float: proportion of samples for training>" << endl;
  59   cout << "  --action-mode=<idle|random|intelligent>" << endl;
  60   cout << "  --task <filename: task to load> <int: degree>" << endl;
  61   exit(e);
  62 }
  63
  64 //////////////////////////////////////////////////////////////////////
  65
  66 int main(int argc, char **argv) {
  67
  68   const int buffer_size = 256;
  69   char intelligence_load_file[buffer_size] = "", intelligence_save_file[buffer_size] = "";
  70
  71   Task *task = 0;
  72   int task_degree = 0;
  73
  74   int nb_ticks = 10000;
  75   int nb_training_iterations = 10;
  76   scalar_t proportion_for_training = -1;
  77
  78   Polygon *grabbed_polygon = 0;
  79   scalar_t relative_grab_x = 0, relative_grab_y = 0;
  80
  81   bool quit = false;
  82   bool press_shift = false;
  83   enum { IDLE, RANDOM, INTELLIGENT } action_mode = IDLE;
  84   bool got_event = true;
  85   int current_action = 0;
  86
  87   scalar_t last_hand_x = 0, last_hand_y = 0;
  88   Polygon *last_grabbing = 0;
  89   bool no_window = false;
  90
  91   //////////////////////////////////////////////////////////////////////
  92   //                    Parsing the shell arguments
  93   //////////////////////////////////////////////////////////////////////
  94
  95   int i = 1;
  96   while(i < argc) {
  97     if(argc == 1 || strcmp(argv[i], "--help") == 0) print_help_and_exit(0);
  98
  99     else if(strcmp(argv[i], "--test") == 0) {
 100       test_approximer();
 101       exit(0);
 102     }
 103
 104     else if(strcmp(argv[i], "--task") == 0) {
 105       check_opt(argc, argv, i, 2, "<filename: task to load> <int: degree>");
 106       if(task) {
 107         cerr << "Can not load two tasks." << endl;
 108         exit(1);
 109       }
 110       task = load_task(argv[i+1]);
 111       task_degree = atoi(argv[i+2]);
 112       i += 3;
 113
 114     } else if(strncmp(argv[i], "--", 2) == 0) {
 115       char variable_name[buffer_size] = "", variable_value[buffer_size] = "";
 116       char *o = argv[i]+2, *s = variable_name, *u = variable_value;
 117       while(*o && *o != '=') *s++ = *o++;
 118       if(*o) {
 119         o++;
 120         while(*o) *u++ = *o++;
 121       }
 122
 123       if(strcmp(variable_name, "nb-ticks") == 0)
 124         nb_ticks = atoi(variable_value);
 125       else if(strcmp(variable_name, "nb-training-iterations") == 0)
 126         nb_training_iterations = atoi(variable_value);
 127       else if(strcmp(variable_name, "proportion-for-training") == 0)
 128         proportion_for_training = atof(variable_value);
 129       else if(strcmp(variable_name, "no-window") == 0)
 130         no_window = true;
 131       else if(strcmp(variable_name, "save-file") == 0)
 132         strcpy(intelligence_save_file, variable_value);
 133       else if(strcmp(variable_name, "load-file") == 0)
 134         strcpy(intelligence_load_file, variable_value);
 135       else if(strcmp(variable_name, "action-mode") == 0) {
 136         if(strcmp(variable_value, "idle") == 0) action_mode = IDLE;
 137         else if(strcmp(variable_value, "random") == 0) action_mode = RANDOM;
 138         else if(strcmp(variable_value, "intelligent") == 0) action_mode = INTELLIGENT;
 139         else {
 140           cerr << "The only known modes are idle, random and intelligent" << endl;
 141           exit(1);
 142         }
 143       } else {
 144         cerr << "Unknown option " << argv[i] << endl;
 145         print_help_and_exit(1);
 146       }
 147       i++;
 148     } else {
 149       cerr << "Unknown option " << argv[i] << endl;
 150       print_help_and_exit(1);
 151     }
 152   }
 153
 154   cout << "FlatLand, a toy universe for goal-planning experiments." << endl;
 155   cout << "$Id: main.cc,v 1.89 2007-06-16 13:51:53 fleuret Exp $" << endl;
 156
 157   if(!task) {
 158     task = load_task("dummy.task");
 159     task_degree = 0;
 160   }
 161
 162   cout << "Loaded task " << task->name()
 163        << " with degree " << task_degree << "/" << task->nb_degrees()
 164        << endl;
 165
 166   if(task_degree < 0 || task_degree >= task->nb_degrees()) {
 167     cout << "Invalid degree: " << task_degree << "." << endl;
 168     exit(1);
 169   }
 170
 171   //////////////////////////////////////////////////////////////////////
 172   //                      Various initializations
 173   //////////////////////////////////////////////////////////////////////
 174
 175   Universe universe(100, task->width(), task->height());
 176   task->init(&universe, task_degree);
 177   Retina retina(&universe);
 178   Manipulator manipulator(task);
 179   manipulator.force_move(task->width()/2, task->height()/2);
 180   retina.set_location(manipulator.hand_x(), manipulator.hand_y());
 181
 182   SimpleWindow *window_main = 0, *window_brain = 0;
 183
 184   int winfd = -1;
 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     window_main = new SimpleWindow("Universe (main window)", 4, 4, task->width(), task->height());
 212     winfd = window_main->file_descriptor();
 213     window_main->map();
 214     cout << "When the main window has the focus, press `q' to quit and click and drag to move" << endl
 215          << "objects." << endl;
 216     window_brain = new SimpleWindow("Universe (brain)",
 217                                      12 + task->width(), 4,
 218                                      retina.width(), retina.height() + manipulator.parameter_height());
 219     window_brain->map();
 220   } else {
 221     cout << "Started without windows." << endl;
 222   }
 223
 224   int tick = 0;
 225   time_t last_t = 0;
 226   scalar_t sum_reward = 0;
 227
 228   //////////////////////////////////////////////////////////////////////
 229   //                         The main loop
 230   //////////////////////////////////////////////////////////////////////
 231
 232   while(!quit && tick != nb_ticks) {
 233
 234     int r;
 235     fd_set fds;
 236
 237
 238     if(window_main) {
 239       struct timeval tv;
 240       FD_ZERO (&fds);
 241       FD_SET (winfd, &fds);
 242       tv.tv_sec = 0;
 243       tv.tv_usec = 5000; // 0.05s
 244       r = select(winfd + 1, &fds, 0, 0, &tv);
 245     } else r = 0;
 246
 247     time_t t = time(0);
 248
 249     if(t > last_t) {
 250       last_t = t;
 251       cout << tick << " " << sum_reward << "              \r"; cout.flush();
 252     }
 253
 254     if(r == 0) { // No window event, thus it's the clock tick
 255
 256         int nb_it = 10;
 257
 258         bool changed = got_event;
 259         got_event = false;
 260
 261         switch(action_mode) {
 262         case IDLE:
 263           break;
 264         case RANDOM:
 265           current_action = manipulator.random_action();
 266           break;
 267         case INTELLIGENT:
 268           current_action = intelligence.best_action();
 269           //           if(drand48() < 0.5) current_action = intelligence.best_action();
 270           //           else                current_action = manipulator.random_action();
 271           break;
 272         }
 273
 274         manipulator.do_action(current_action);
 275
 276         scalar_t dt = 1.0/scalar_t(nb_it);
 277         for(int k = 0; k < nb_it; k++) {
 278           manipulator.update(dt, &universe);
 279           task->update(dt, &universe, &manipulator);
 280           changed |= universe.update(dt);
 281         }
 282
 283         tick++;
 284
 285         changed |= manipulator.hand_x() != last_hand_x ||
 286           manipulator.hand_y() != last_hand_y ||
 287           manipulator.grabbing() != last_grabbing;
 288
 289         scalar_t reward = task->reward(&universe, &manipulator);
 290         sum_reward += abs(reward);
 291         intelligence.update(current_action, reward);
 292         expanded_map.update_map();
 293
 294         if(changed) {
 295           last_hand_x = manipulator.hand_x();
 296           last_hand_y = manipulator.hand_y();
 297           last_grabbing = manipulator.grabbing();
 298           retina.set_location(manipulator.hand_x(), manipulator.hand_y());
 299
 300           if(window_main) {
 301             window_main->color(0.0, 0.0, 0.0);
 302             window_main->fill();
 303             task->draw(window_main);
 304             universe.draw(window_main);
 305             manipulator.draw_on_universe(window_main);
 306             retina.draw_on_universe(window_main);
 307
 308             if(grabbed_polygon) {
 309               int x, y, delta = 3;
 310               x = int(grabbed_polygon->absolute_x(relative_grab_x, relative_grab_y));
 311               y = int(grabbed_polygon->absolute_y(relative_grab_x, relative_grab_y));
 312               window_main->color(0.0, 0.0, 0.0);
 313               window_main->draw_line(x - delta, y, x + delta, y);
 314               window_main->draw_line(x, y - delta, x, y + delta);
 315             }
 316
 317             window_main->show();
 318
 319             if(window_brain) {
 320               retina.draw_parameters(0, 0, window_brain);
 321               manipulator.draw_parameters(0, retina.height() + 1, window_brain);
 322               window_brain->show();
 323             }
 324           }
 325         }
 326
 327     } else if(r > 0) { // We got window events, let's process them
 328
 329       got_event = true;
 330
 331       if(FD_ISSET(winfd, &fds)) {
 332
 333         SimpleEvent se;
 334
 335         do {
 336           se = window_main->event();
 337
 338           switch(se.type) {
 339
 340           case SimpleEvent::MOUSE_CLICK_PRESS:
 341             {
 342               switch(se.button) {
 343
 344               case 1:
 345                 if(press_shift) {
 346                   manipulator.force_move(se.x, se.y);
 347                   manipulator.do_action(Manipulator::ACTION_GRAB);
 348                 } else {
 349                   grabbed_polygon = universe.pick_polygon(se.x, se.y);
 350                   if(grabbed_polygon) {
 351                     relative_grab_x = grabbed_polygon->relative_x(se.x, se.y);
 352                     relative_grab_y = grabbed_polygon->relative_y(se.x, se.y);
 353                   }
 354                 }
 355                 break;
 356               case 4:
 357                 {
 358                   Polygon *g = universe.pick_polygon(se.x, se.y);
 359                   if(g) g->_theta += M_PI/32;
 360                 }
 361                 break;
 362               case 5:
 363                 {
 364                   Polygon *g = universe.pick_polygon(se.x, se.y);
 365                   if(g) g->_theta -= M_PI/32;
 366                 }
 367                 break;
 368               }
 369             }
 370             break;
 371
 372           case SimpleEvent::MOUSE_CLICK_RELEASE:
 373             switch(se.button) {
 374             case 1:
 375               if(press_shift) manipulator.do_action(Manipulator::ACTION_RELEASE);
 376               else            grabbed_polygon = 0;
 377               break;
 378             default:
 379               break;
 380             }
 381
 382           case SimpleEvent::MOUSE_MOTION:
 383             {
 384               if(press_shift) manipulator.force_move(se.x, se.y);
 385               else {
 386                 if(grabbed_polygon) {
 387                   scalar_t xf, yf, force_x, force_y, f, fmax = 100;
 388                   xf = grabbed_polygon->absolute_x(relative_grab_x, relative_grab_y);
 389                   yf = grabbed_polygon->absolute_y(relative_grab_x, relative_grab_y);
 390                   force_x = se.x - xf;
 391                   force_y = se.y - yf;
 392                   f = sqrt(sq(force_x) + sq(force_y));
 393                   if(f > fmax) { force_x = (force_x * fmax)/f; force_y = (force_y * fmax)/f; }
 394                   grabbed_polygon->apply_force(0.1, xf, yf, force_x, force_y);
 395                 }
 396               }
 397               break;
 398             }
 399             break;
 400
 401           case SimpleEvent::KEY_PRESS:
 402             {
 403               if(strcmp(se.key, "q") == 0) quit = true;
 404               else if(strcmp(se.key, "s") == 0) {
 405                 retina.save_as_ppm("/tmp/retina.ppm");
 406                 cout << "Retina screen shot saved in /tmp/retina.ppm" << endl;
 407                 {
 408                   ofstream out("/tmp/universe.fig");
 409                   universe.print_fig(out);
 410                 }
 411               }
 412               else if(strcmp(se.key, "Shift_L") == 0 || strcmp(se.key, "Shift_R") == 0) press_shift = true;
 413
 414               else if(strcmp(se.key, "Up") == 0) manipulator.do_action(Manipulator::ACTION_MOVE_UP);
 415               else if(strcmp(se.key, "Right") == 0) manipulator.do_action(Manipulator::ACTION_MOVE_RIGHT);
 416               else if(strcmp(se.key, "Down") == 0) manipulator.do_action(Manipulator::ACTION_MOVE_DOWN);
 417               else if(strcmp(se.key, "Left") == 0) manipulator.do_action(Manipulator::ACTION_MOVE_LEFT);
 418               else if(strcmp(se.key, "g") == 0) manipulator.do_action(Manipulator::ACTION_GRAB);
 419               else if(strcmp(se.key, "r") == 0) manipulator.do_action(Manipulator::ACTION_RELEASE);
 420
 421               else if(strcmp(se.key, "space") == 0) {
 422                 switch(action_mode) {
 423                 case IDLE:
 424                   action_mode = RANDOM;
 425                   cout << "Switched to random mode" << endl;
 426                   break;
 427                 case RANDOM:
 428                   action_mode = INTELLIGENT;
 429                   cout << "Switched to intelligent mode" << endl;
 430                   break;
 431                 case INTELLIGENT:
 432                   cout << "Switched to idle mode" << endl;
 433                   action_mode = IDLE;
 434                   break;
 435                 }
 436               }
 437
 438               else cout << "Undefined key " << se.key << endl;
 439             }
 440             break;
 441
 442           case SimpleEvent::KEY_RELEASE:
 443             {
 444               if(strcmp(se.key, "Shift_L") == 0 || strcmp(se.key, "Shift_R") == 0) press_shift = false;
 445             }
 446             break;
 447
 448           default:
 449             break;
 450
 451           }
 452         } while(se.type != SimpleEvent::NO_EVENT);
 453       } else {
 454         cerr << "Error on select: " << strerror(errno) << endl;
 455         exit(1);
 456       }
 457     }
 458   }
 459
 460   if(proportion_for_training > 0) {
 461     cout << "Learning ... "; cout.flush();
 462     intelligence.learn(proportion_for_training);
 463     cout << "done." << endl;
 464   }
 465
 466   if(intelligence_save_file[0]) {
 467     cout << "Saving to " << intelligence_save_file << endl; cout.flush();
 468     ofstream os(intelligence_save_file);
 469     if(os.fail()) {
 470       cerr << "error writing " << intelligence_save_file << "." << endl;
 471       exit(1);
 472     }
 473     cout << "done." << endl;
 474     intelligence.save(os);
 475   }
 476
 477   delete window_brain;
 478   delete window_main;
 479
 480 }