reinforcement_learning fix reward threshold

Author: pbartet

reinforcement_learning/actor_critic.py

@@ -99,7 +99,7 @@ def finish_episode():
     if i_episode % args.log_interval == 0:
         print('Episode {}\tLast length: {:5d}\tAverage length: {:.2f}'.format(
             i_episode, t, running_reward))
-    if running_reward > 200:
+    if running_reward > env.spec.reward_threshold:
         print("Solved! Running reward is now {} and "
               "the last episode runs to {} time steps!".format(running_reward, t))
         break

reinforcement_learning/reinforce.py

@@ -89,7 +89,7 @@ def finish_episode():
     if i_episode % args.log_interval == 0:
         print('Episode {}\tLast length: {:5d}\tAverage length: {:.2f}'.format(
             i_episode, t, running_reward))
-    if running_reward > 200:
+    if running_reward > env.spec.reward_threshold:
         print("Solved! Running reward is now {} and "
               "the last episode runs to {} time steps!".format(running_reward, t))
         break