diff --git a/travail_de_groupe/jeu_appren_par_renfo/src/main.c b/travail_de_groupe/jeu_appren_par_renfo/src/main.c
index 084b9de618c8397569bf386c7b4e25a4f6b83b45..f16624fdcda502583afb8f349c7540ea326e5e06 100644
--- a/travail_de_groupe/jeu_appren_par_renfo/src/main.c
+++ b/travail_de_groupe/jeu_appren_par_renfo/src/main.c
@@ -5,14 +5,20 @@ int game_state;
int main(){
+ agent_t * agent;
+ int i ;
float ***** Q = allocateAndInitiateQ();
+ srand ( time(NULL));
+ agent =initAgent();
writeQ(Q);
running = 1;
+ i=setReward( agent->x , agent->y, 0);
+ printf("%d \n ",i );
game_state = GAME;
readMapFromFile("map.txt");
initPlayer();
initKeys();
-
+
mainLoop();
}
\ No newline at end of file
diff --git a/travail_de_groupe/jeu_appren_par_renfo/src/qlearn.c b/travail_de_groupe/jeu_appren_par_renfo/src/qlearn.c
index efed9ae37434db73c3149decbc4153655e142796..9b06103b077fa0d1a16e95df582ecd59adc7dbd7 100644
--- a/travail_de_groupe/jeu_appren_par_renfo/src/qlearn.c
+++ b/travail_de_groupe/jeu_appren_par_renfo/src/qlearn.c
@@ -1,5 +1,20 @@
#include "qlearn.h"
+agent_t * initAgent (){
+ agent_t * agent =(agent_t*)malloc(sizeof(agent_t));
+ if (agent ==NULL){
+ printf("erreur alloc\n ");
+ exit (1);
+ }
+ agent->x=(16+rand()%16)*BLOCK_SIZE;
+ agent->y=(1+rand()%14)*BLOCK_SIZE;
+ agent->high=2*BLOCK_SIZE;
+ agent->weight=2*BLOCK_SIZE;
+ agent->speed = 1;
+ // si changement de speed => changement de collisiosn dans le takeaction
+ return(agent);
+}
+
void moveAgent(agent_t * agent, int choice){
switch (choice)
{
@@ -115,6 +130,8 @@ int argmax(float * arr){
int convertIntoZone(int xAgent,int yAgent){
int zone;
+ xAgent=xAgent/BLOCK_SIZE;
+ yAgent=yAgent/BLOCK_SIZE;
if(xAgent<23 && yAgent<=8){zone=0;}
else if(xAgent<31 && yAgent<=8){zone=1;}
else if(xAgent<23 && yAgent<=18){zone=2;}
@@ -146,43 +163,43 @@ int converterIntoAngleH(float angleH){
return(angleZone);
}
-int takeAction(int xagent, int yagent, float ***** Q, int canonZone, int angleHZone, int angleFZone, float eps){
+int takeAction(int xAgent, int yAgent, float ***** Q, int canonZone, int angleHZone, int angleFZone, float eps){
int action;
int proba = rand() % 100;
int receiverZone=0;
if (proba < eps * 100){
- if (xagent > (MAP_WIDTH-1)/2+1 && xagent < MAP_WIDTH- 2 && yagent > 1 && yagent < MAP_HEIGHT - 2){
+ if (xAgent/BLOCK_SIZE > (MAP_WIDTH-1)/2+1 && xAgent/BLOCK_SIZE < MAP_WIDTH- 2 && yAgent/BLOCK_SIZE > 1 && yAgent/BLOCK_SIZE < MAP_HEIGHT - 2){
action = rand() % 5;// OK cas au centre
}
- else if (xagent == (MAP_WIDTH-1)/2+1 && yagent > 1 && yagent < MAP_HEIGHT - 2){
+ else if (xAgent/BLOCK_SIZE == (MAP_WIDTH-1)/2+1 && yAgent/BLOCK_SIZE > 1 && yAgent/BLOCK_SIZE < MAP_HEIGHT - 2){
int possibleActions[4] = {1, 2, 3,4};
action = possibleActions[rand() % 4];// OK cas filet
}
- else if (xagent == (MAP_WIDTH-1)/2+1 && yagent == 1){
+ else if (xAgent/BLOCK_SIZE == (MAP_WIDTH-1)/2+1 && yAgent/BLOCK_SIZE== 1){
int possibleActions[3] = {1, 3, 4};
action = possibleActions[rand() % 3];// cas en haut a gauche
}
- else if (xagent == (MAP_WIDTH-1)/2+1 && yagent==MAP_HEIGHT - 2){
+ else if (xAgent/BLOCK_SIZE == (MAP_WIDTH-1)/2+1 && yAgent/BLOCK_SIZE==MAP_HEIGHT - 2){
int possibleActions[3] = {1, 2, 4};
action = possibleActions[rand() % 3];// cas en bas a gauche
}
- else if (yagent ==1 && xagent > (MAP_WIDTH-1)/2+1 && xagent < MAP_WIDTH- 2){
+ else if (yAgent/BLOCK_SIZE ==1 && xAgent/BLOCK_SIZE > (MAP_WIDTH-1)/2+1 && xAgent/BLOCK_SIZE < MAP_WIDTH- 2){
int possibleActions[4] = {0, 1,3,4};
action = possibleActions[rand() % 4];// cas en haut au milieu
}
- else if (xagent == MAP_WIDTH- 2 && yagent == 1){
+ else if (xAgent/BLOCK_SIZE == MAP_WIDTH- 2 && yAgent/BLOCK_SIZE == 1){
int possibleActions[3] = {0, 3,4};
action = possibleActions[rand() % 3];// cas en haut a droite
}
- else if (xagent == MAP_WIDTH-2 && yagent <MAP_HEIGHT-2 && yagent>1){
+ else if (xAgent/BLOCK_SIZE == MAP_WIDTH-2 && yAgent/BLOCK_SIZE <MAP_HEIGHT-2 && yAgent/BLOCK_SIZE>1){
int possibleActions[4] = {0,2,3,4};
action = possibleActions[rand() % 4];// cas a droite au milieu
}
- else if (xagent == MAP_WIDTH-2 && yagent == MAP_HEIGHT-2){
+ else if (xAgent/BLOCK_SIZE== MAP_WIDTH-2 && yAgent/BLOCK_SIZE == MAP_HEIGHT-2){
int possibleActions[3] = {0, 2,4};
action = possibleActions[rand() % 3];// cas en bas a droite
}
- else if (xagent > (MAP_WIDTH-1)/2+1 && xagent < MAP_WIDTH- 2 && yagent == MAP_HEIGHT-2){
+ else if (xAgent/BLOCK_SIZE > (MAP_WIDTH-1)/2+1 && xAgent/BLOCK_SIZE < MAP_WIDTH- 2 && yAgent/BLOCK_SIZE == MAP_HEIGHT-2){
int possibleActions[4] = {0,1,2,4};
action = possibleActions[rand() % 4];
}
@@ -191,9 +208,45 @@ int takeAction(int xagent, int yagent, float ***** Q, int canonZone, int angleHZ
}
}
else{
- receiverZone= convertIntoZone(xagent,yagent);
+ receiverZone= convertIntoZone(xAgent/BLOCK_SIZE,yAgent/BLOCK_SIZE);
action = argmax(Q[receiverZone][canonZone][angleHZone][angleFZone]);
//printf("wtf");
}
return action;
-}
\ No newline at end of file
+}
+
+void insertPointToLine(ptline_t head, int receiverZone, int canonZone, int angleHZone, int angleFZone){
+ ptline_t newPoint = (ptline_t )malloc(sizeof(line_t));
+ if (newPoint==NULL){
+ printf("error malloc\n ");
+ exit(1);
+ }
+ newPoint->receiverZone = receiverZone;
+ newPoint->shooterZone = canonZone;
+ newPoint-> angleHZone= angleHZone;
+ newPoint->angleFZone=angleFZone;
+ newPoint->next =head;// problème pt
+ head = newPoint;
+}
+
+void freeLine ( ptline_t headLine){
+ ptline_t current= headLine;
+ while ( current !=NULL){
+ ptline_t temporary = current;
+ current = current ->next;
+ free(temporary);
+ }
+}
+
+int setReward(int xAgent, int yAgent, int dropZone){
+ int zoneAgent;
+ int reward=0;
+
+ zoneAgent= convertIntoZone( xAgent,yAgent);
+ if (zoneAgent==dropZone){
+ reward=1;
+ }
+ return (reward);
+}
+
+
diff --git a/travail_de_groupe/jeu_appren_par_renfo/src/qlearn.h b/travail_de_groupe/jeu_appren_par_renfo/src/qlearn.h
index 830c3054f54a1721a18c77c001a58ead858753cd..15cf2773f949b6b0dc8f461c4d4b4bb1d486d04b 100644
--- a/travail_de_groupe/jeu_appren_par_renfo/src/qlearn.h
+++ b/travail_de_groupe/jeu_appren_par_renfo/src/qlearn.h
@@ -23,12 +23,21 @@
typedef struct agent {
int x;
int y;
- int heigth;
+ int high;
int weight;
int speed;
} agent_t;
+typedef struct line {
+ int receiverZone;
+ int shooterZone;
+ int angleHZone;
+ int angleFZone;
+ struct line *next ;
+}line_t,*ptline_t;
+
+agent_t* initAgent ( );
void moveAgent(agent_t * agent, int choice);
float ***** allocateAndInitiateQ();
void writeQ(float *****);
@@ -37,4 +46,7 @@ int convertIntoZone(int ,int y);
int converterIntoAngleF(float);
int converterIntoAngleH(float);
int takeAction(int ,int , float ***** , int , int, int, float );
+void insertPointToLine(ptline_t head, int, int , int , int);
+void freeLine ( ptline_t makeheadLine);
+int setReward(int , int , int );
#endif
\ No newline at end of file