New curriculum, new model

config/ppo/Sorter_curriculum.yaml

         gamma: 0.99
         strength: 1.0
     keep_checkpoints: 5
-    max_steps: 10000000
+    max_steps: 5000000
     time_horizon: 256
     summary_freq: 10000
     threaded: true
           behavior: Sorter
           signal_smoothing: true
           min_lesson_length: 100
-          threshold: 0.5
+          threshold: 0.3
         value: 2.0
       - name: Lesson1
         completion_criteria:
           min_lesson_length: 100
-          threshold: 0.6
+          threshold: 0.4
         value: 4.0
       - name: Lesson2
         completion_criteria:
           min_lesson_length: 100
-          threshold: 0.65
+          threshold: 0.45
         value: 6.0
       - name: Lesson3
         completion_criteria:
           min_lesson_length: 100
-          threshold: 0.7
+          threshold: 0.5
         value: 8.0
       - name: Lesson4
         completion_criteria:
           min_lesson_length: 100
-          threshold: 0.75
+          threshold: 0.55
         value: 10.0
       - name: Lesson5
         completion_criteria:
           min_lesson_length: 100
-          threshold: 0.8
+          threshold: 0.6
         value: 12.0
       - name: Lesson6
         completion_criteria:
           min_lesson_length: 100
-          threshold: 0.85
+          threshold: 0.65
         value: 14.0
       - name: Lesson7
         completion_criteria:
           min_lesson_length: 100
-          threshold: 0.9
+          threshold: 0.7
         value: 16.0
       - name: Lesson8
         completion_criteria:
           min_lesson_length: 100
-          threshold: 0.95
+          threshold: 0.75
         value: 18.0
       - name: Lesson9
         value: 20.0