java - ArrayIndexOutOfBoundsException:-1 -

i'm coding rl behaviors on pacman bot , messed things 1 of lists in 1 of functions arg_allmax or chooseaction

here code of class:

package rl;  import java.util.arraylist; import java.util.hashtable;  public class qlearn {     private double epsilon = 0.1; // epsilon parameter epsilon greedy strategy      private double alpha = 0.2; // alpha parameter: used influence o refresh of q     private double gamma = 0.9; // used notice or not feedback of next action ; if =0 -> no feed  private int actions[]; private hashtable< tuple<integer,integer>, double> q; // q(s,a) : hashtable : <state,action> -> value of q   public qlearn(int[] actions) {     this.actions = actions;     q = new hashtable< tuple<integer,integer>, double>(); }  public qlearn(int[] actions, double epsilon, double alpha, double gamma) {     this.actions = actions;     this.epsilon = epsilon;     this.alpha = alpha;     this.gamma = gamma;     q = new hashtable< tuple<integer,integer>, double>(); }  public double getq(int id_state, int id_action) {     // value of q state of id_state , action id_action ( return 0 if value not in hashtable )      tuple<integer,integer> t = new tuple<integer,integer> (id_state, id_action); // creatte new integer object tubple value of id_state , id_action      double v = q.get(t);     if(v != null) return v;     else return 0.0; }  // argmax of list public int argmax(double[] list) {     int arg=-1;     double max= 0;     ( int = 0; i<list.length; i++){         if ( list[i]>max ){             max = list[i];             arg = i;         }     }     return arg; }  // argmax if argmax has several iterations public arraylist<integer> arg_allmax(double[] list) {     arraylist<integer> args = new arraylist<integer>();     int = argmax(list);     ( int = 0; i< list.length; i++){         if (list[i] == list[a]){             args.add(i);         }     }     return args; }  // max of list public double max(double[] list) {     double max_ = -1e20;     int = argmax(list);     max_ = list[a];     return max_; }   /*  * fonction updates hashtable  *      action  id_action , state  id_state  *      if q(s,a) had old value, allocate new value+ alpha(value - old_value)  *      if q(s,a) had not old value : allocate reward  */ public void learnq(int id_state, int id_action, double reward, double value) {     tuple<integer,integer> t = new tuple<integer,integer>(id_state,id_action);     double oldv = q.get(t);      if(oldv == null) {          q.put(t, reward);     } else {          q.put(t, oldv+alpha*(value-oldv));     } }  /*  * here epsilon greedy strategy  *      proba epsilon :we choose random action  *      avec proba 1-eps : choose favorable action in fonction of  q(s,a)  */ public int chooseaction(int id_state) {     int action = -1;     if(math.random() < epsilon) {          int = (int)(math.random()*actions.length);         action = actions[i];      } else {          double[] tab = new double[actions.length];         arraylist<integer> argmaxarray = new arraylist<integer>();         ( int i=0; i>actions.length; i++){             tab[i]=actions[i];         }         argmaxarray=arg_allmax(tab);         int i=(int)(math.random()*argmaxarray.size());         action=argmaxarray.get(i);      }      return action; }   /*  * learning after occurence of move  *      1) profitable potential action  q(s',a)  *      2) call learnq  */ public void learn(int id_state1, int id_action1, double reward, int id_state2) {     int futureaction = 0;     futureaction = chooseaction(id_state2);     double maxqnew = 0; // remplir       maxqnew = getq(futureaction, id_state2);       learnq(id_state1, id_action1, reward, reward + gamma*maxqnew);  }  // affiche q(s,a) private void printqvalue(int id_state) {     for(int action : actions) {         tuple<integer,integer> t = new tuple<integer,integer>(id_state,action);         double v = q.get(t);         system.out.print(v+" ");     }     system.out.println(); } 

here eclipse tells me :

exception in thread "awt-eventqueue-0" java.lang.arrayindexoutofboundsexception: -1     @ rl.qlearn.arg_allmax(qlearn.java:54)     @ rl.qlearn.chooseaction(qlearn.java:108)     @ rl.qlearn.learn(qlearn.java:138) 

i think comes somewhere in else of chooseaction method using all_argmax fonction cannot find exact error!

here 2 involved methods (so it's more readable you):

all_argmax :

public arraylist<integer> arg_allmax(double[] list) {     arraylist<integer> args = new arraylist<integer>();     int = argmax(list);     ( int = 0; i< list.length; i++){         if (list[i] == list[a]){             args.add(i);         }     }     return args; } 

chooseaction :

public int chooseaction(int id_state) {     int action = -1;     if(math.random() < epsilon) {          int = (int)(math.random()*actions.length);         action = actions[i];      } else {          double[] tab = new double[actions.length];         arraylist<integer> argmaxarray = new arraylist<integer>();         ( int i=0; i>actions.length; i++){             tab[i]=actions[i];         }         argmaxarray=arg_allmax(tab);         int i=(int)(math.random()*argmaxarray.size());         action=argmaxarray.get(i);      }      return action; } 

your indexoutofboundsexception occurs because of argmax([]) method, either because of empty array or because doubles in list negative.

in either of these cases int arg = -1 variable never set value -1, out of bounds in scenario since -1 not valid array position.

the best course of action either check if array empty before passing argmax or checking if return value valid (not -1) before doing it. , changing double max = 0 double max = double.negative_infinity