Add new trainer config for walljump

config/sac_trainer_config.yaml

     hidden_units: 256
     summary_freq: 2000
     time_horizon: 128
-    init_entcoef: 0.1
+    init_entcoef: 0.5
+    batch_size: 64
-    init_entcoef: 0.1
-    normalize: false
+    init_entcoef: 0.5
+    normalize: true
+    reward_signals:
+        extrinsic:
+            strength: 1.0
+            gamma: 0.99
+        curiosity:
+            strength: 0.02
+            gamma: 0.99
+            encoding_size: 256
 
 StrikerLearning:
     max_steps: 5.0e5