oxbrbtx/PrimAITE
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

901 - Changed the default expected_mean_reward_per_episode values in test_seeding_and_deterministic_session.py

Browse Source
This commit is contained in:
SunilSamra
2023-07-14 14:26:10 +01:00
parent 8c0ca8cfbc
commit e5debcfc6c
1 changed files with 13 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
tests/test_seeding_and_deterministic_session.py
View File

@@ -26,16 +26,16 @@ def test_seeded_learning(temp_primaite_session):
now work. If not, then you've got a bug :). now work. If not, then you've got a bug :).
""" """
expected_mean_reward_per_episode = { expected_mean_reward_per_episode = {
1: -33.90625, 1: -30.703125,
2: -32.32421875, 2: -29.94140625,
3: -25.234375, 3: -27.91015625,
4: -30.15625, 4: -29.66796875,
5: -27.1484375, 5: -32.44140625,
6: -29.609375, 6: -30.33203125,
7: -29.921875, 7: -26.25,
8: -29.3359375, 8: -22.44140625,
9: -28.046875, 9: -30.3125,
10: -27.24609375, 10: -28.359375,
} }
with temp_primaite_session as session: with temp_primaite_session as session:
@@ -44,6 +44,9 @@ def test_seeded_learning(temp_primaite_session):
), "Expected output is based upon a agent that was trained with seed 67890" ), "Expected output is based upon a agent that was trained with seed 67890"
session.learn() session.learn()
print("\n")
print(session.learn_av_reward_per_episode())
assert expected_mean_reward_per_episode == session.learn_av_reward_per_episode() assert expected_mean_reward_per_episode == session.learn_av_reward_per_episode()