long tennis/soccer runs

config/trainer_config.yaml

             gamma: 0.995
 
 Tennis:
-    max_steps: 5.0e7
+    max_steps: 1.0e8
     learning_rate_schedule: constant
     batch_size: 2048
     buffer_size: 20480
     time_horizon: 1000
     self_play:
-        window: 10
+        window: 100
-        swap_steps: 50000
+        swap_steps: 2000
         team_change: 100000
 
 Goalie:
 
 SoccerTwos:
     normalize: false
-    max_steps: 5.0e7
+    max_steps: 1.0e8
     learning_rate_schedule: constant
     batch_size: 2048
     buffer_size: 20480
     self_play:
-        window: 10
+        window: 100
-        swap_steps: 50000
+        swap_steps: 2000
         team_change: 200000
 
 SmallCubeSoldier: