add TD algorithms and started adopting to continous tasks

- add Q-Learning and SARSA
- more config variables
This commit is contained in:
2020-02-17 13:56:55 +01:00
parent f4f1f7bd37
commit 77898f4e5a
16 changed files with 222 additions and 63 deletions
@@ -30,7 +30,6 @@ public class StateActionRow<A extends Enum> extends JTextArea {
protected void refreshLabels(){
if(state == null || actionValues == null) return;
System.out.println("refreshing");
StringBuilder sb = new StringBuilder(state.toString()).append("\n");
for(Map.Entry<A, Double> actionValue: actionValues.entrySet()){
sb.append("\t").append(actionValue.getKey()).append("\t").append(actionValue.getValue()).append("\n");