mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-28 01:07:11 +00:00
c364506710
* Ditch most of the seeding.py and replace np_random with the numpy default_rng. Let's see if tests pass * Updated a bunch of RNG calls from the RandomState API to Generator API * black; didn't expect that, did ya? * Undo a typo * blaaack * More typo fixes * Fixed setting/getting state in multidiscrete spaces * Fix typo, fix a test to work with the new sampling * Correctly (?) pass the randomly generated seed if np_random is called with None as seed * Convert the Discrete sample to a python int (as opposed to np.int64) * Remove some redundant imports * First version of the compatibility layer for old-style RNG. Mainly to trigger tests. * Removed redundant f-strings * Style fixes, removing unused imports * Try to make tests pass by removing atari from the dockerfile * Try to make tests pass by removing atari from the setup * Try to make tests pass by removing atari from the setup * Try to make tests pass by removing atari from the setup * First attempt at deprecating `env.seed` and supporting `env.reset(seed=seed)` instead. Tests should hopefully pass but throw up a million warnings. * black; didn't expect that, didya? * Rename the reset parameter in VecEnvs back to `seed` * Updated tests to use the new seeding method * Removed a bunch of old `seed` calls. Fixed a bug in AsyncVectorEnv * Stop Discrete envs from doing part of the setup (and using the randomness) in init (as opposed to reset) * Add explicit seed to wrappers reset * Remove an accidental return * Re-add some legacy functions with a warning. * Use deprecation instead of regular warnings for the newly deprecated methods/functions
62 lines
2.3 KiB
Python
62 lines
2.3 KiB
Python
import unittest
|
|
import numpy as np
|
|
from gym import envs
|
|
from tests.envs.spec_list import skip_mujoco, SKIP_MUJOCO_WARNING_MESSAGE
|
|
|
|
|
|
def verify_environments_match(
|
|
old_environment_id, new_environment_id, seed=1, num_actions=1000
|
|
):
|
|
old_environment = envs.make(old_environment_id)
|
|
new_environment = envs.make(new_environment_id)
|
|
|
|
old_reset_observation = old_environment.reset(seed=seed)
|
|
new_reset_observation = new_environment.reset(seed=seed)
|
|
|
|
np.testing.assert_allclose(old_reset_observation, new_reset_observation)
|
|
|
|
for i in range(num_actions):
|
|
action = old_environment.action_space.sample()
|
|
old_observation, old_reward, old_done, old_info = old_environment.step(action)
|
|
new_observation, new_reward, new_done, new_info = new_environment.step(action)
|
|
|
|
eps = 1e-6
|
|
np.testing.assert_allclose(old_observation, new_observation, atol=eps)
|
|
np.testing.assert_allclose(old_reward, new_reward, atol=eps)
|
|
np.testing.assert_allclose(old_done, new_done, atol=eps)
|
|
|
|
for key in old_info:
|
|
np.testing.assert_allclose(old_info[key], new_info[key], atol=eps)
|
|
|
|
|
|
@unittest.skipIf(skip_mujoco, SKIP_MUJOCO_WARNING_MESSAGE)
|
|
class Mujocov2Tov3ConversionTest(unittest.TestCase):
|
|
def test_environments_match(self):
|
|
test_cases = (
|
|
{"old_id": "Swimmer-v2", "new_id": "Swimmer-v3"},
|
|
{"old_id": "Hopper-v2", "new_id": "Hopper-v3"},
|
|
{"old_id": "Walker2d-v2", "new_id": "Walker2d-v3"},
|
|
{"old_id": "HalfCheetah-v2", "new_id": "HalfCheetah-v3"},
|
|
{"old_id": "Ant-v2", "new_id": "Ant-v3"},
|
|
{"old_id": "Humanoid-v2", "new_id": "Humanoid-v3"},
|
|
)
|
|
|
|
for test_case in test_cases:
|
|
verify_environments_match(test_case["old_id"], test_case["new_id"])
|
|
|
|
# Raises KeyError because the new envs have extra info
|
|
with self.assertRaises(KeyError):
|
|
verify_environments_match("Swimmer-v3", "Swimmer-v2")
|
|
|
|
# Raises KeyError because the new envs have extra info
|
|
with self.assertRaises(KeyError):
|
|
verify_environments_match("Humanoid-v3", "Humanoid-v2")
|
|
|
|
# Raises KeyError because the new envs have extra info
|
|
with self.assertRaises(KeyError):
|
|
verify_environments_match("Swimmer-v3", "Swimmer-v2")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|