Merge branch 'antWorldRewardAnalysis'

# Conflicts:
#	src/main/java/core/algo/EpisodicLearning.java
#	src/main/java/core/controller/RLController.java
#	src/main/java/evironment/jumpingDino/DinoWorld.java
#	src/main/java/evironment/jumpingDino/DinoWorldAdvanced.java
#	src/main/java/example/JumpingDino.java

src/main/java/core/controller/RLController.java

@@ -7,7 +7,7 @@ import core.ListDiscreteActionSpace;
 import core.algo.EpisodicLearning;
 import core.algo.Learning;
 import core.algo.Method;
-import core.algo.mc.MonteCarloControlFirstVisitEGreedy;
+import core.algo.mc.MonteCarloControlEGreedy;
 import core.algo.td.QLearningOffPolicyTDControl;
 import core.algo.td.SARSA;
 import core.listener.LearningListener;
@@ -49,9 +49,13 @@ public class RLController<A extends Enum> implements LearningListener {
     public void start() {
         switch(method) {
             case MC_CONTROL_FIRST_VISIT:
-                learning = new MonteCarloControlFirstVisitEGreedy<>(environment, discreteActionSpace, discountFactor, epsilon, delay);
+                learning = new MonteCarloControlEGreedy<>(environment, discreteActionSpace, discountFactor, epsilon, delay);
                 break;
-            case SARSA_EPISODIC:
+            case MC_CONTROL_EVERY_VISIT:
+                learning = new MonteCarloControlEGreedy<>(environment, discreteActionSpace, discountFactor, epsilon, delay, true);
+                break;
+
+            case SARSA_ON_POLICY_CONTROL:
                 learning = new SARSA<>(environment, discreteActionSpace, discountFactor, epsilon, learningRate, delay);
                 break;
             case Q_LEARNING_OFF_POLICY_CONTROL:
@@ -67,17 +71,17 @@ public class RLController<A extends Enum> implements LearningListener {
     }
 
     protected void initListeners() {
-        learning.addListener(this);
-        new Thread(() -> {
-            while(true) {
-                printNextEpisode = true;
-                try {
-                    Thread.sleep(30 * 1000);
-                } catch (InterruptedException e) {
-                    e.printStackTrace();
+            learning.addListener(this);
+            new Thread(() -> {
+                while(learning.isCurrentlyLearning()) {
+                    printNextEpisode = true;
+                    try {
+                        Thread.sleep(30 * 1000);
+                    } catch (InterruptedException e) {
+                        e.printStackTrace();
+                    }
                 }
-            }
-        }).start();
+            }).start();
     }
 
     private void initLearning() {