Fix reward threshold in test_identity.py (#767)

Stable-Baselines-Team · Mar 26, 2020 · 950c2a5 · 950c2a5
1 parent ac92d2e
commit 950c2a5
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/docs/misc/changelog.rst b/docs/misc/changelog.rst
@@ -22,6 +22,7 @@ Bug Fixes:
 - Fixed SAC/TD3 checking time to update on learn steps instead of total steps (@solliet)
 - Added ``**kwarg`` pass through for ``reset`` method in ``atari_wrappers.FrameStack`` (@solliet)
 - Fix consistency in ``setup_model()`` for SAC, ``target_entropy`` now uses ``self.action_space`` instead of ``self.env.action_space`` (@solliet)
+- Fix reward threshold in ``test_identity.py``
 
 Deprecations:
 ^^^^^^^^^^^^^

diff --git a/tests/test_identity.py b/tests/test_identity.py
@@ -39,7 +39,7 @@ def test_identity(model_name):
     env = DummyVecEnv([lambda: IdentityEnv(10)])
 
     model = LEARN_FUNC_DICT[model_name](env)
-    evaluate_policy(model, env, n_eval_episodes=20, reward_threshold=0.9)
+    evaluate_policy(model, env, n_eval_episodes=20, reward_threshold=90)
 
     obs = env.reset()
     assert model.action_probability(obs).shape == (1, 10), "Error: action_probability not returning correct shape"
@@ -72,6 +72,6 @@ def test_identity_continuous(model_class):
                          action_noise=action_noise, buffer_size=int(1e6))
     model.learn(total_timesteps=20000)
 
-    evaluate_policy(model, env, n_eval_episodes=20, reward_threshold=0.9)
+    evaluate_policy(model, env, n_eval_episodes=20, reward_threshold=90)
     # Free memory
     del model, env