mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-09-03 10:55:01 +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 pytest
|
|
import numpy as np
|
|
|
|
from gym.spaces import Tuple
|
|
from tests.vector.utils import CustomSpace, make_env
|
|
|
|
from gym.vector.async_vector_env import AsyncVectorEnv
|
|
from gym.vector.sync_vector_env import SyncVectorEnv
|
|
from gym.vector.vector_env import VectorEnv
|
|
|
|
|
|
@pytest.mark.parametrize("shared_memory", [True, False])
|
|
def test_vector_env_equal(shared_memory):
|
|
env_fns = [make_env("CubeCrash-v0", i) for i in range(4)]
|
|
num_steps = 100
|
|
try:
|
|
async_env = AsyncVectorEnv(env_fns, shared_memory=shared_memory)
|
|
sync_env = SyncVectorEnv(env_fns)
|
|
|
|
assert async_env.num_envs == sync_env.num_envs
|
|
assert async_env.observation_space == sync_env.observation_space
|
|
assert async_env.single_observation_space == sync_env.single_observation_space
|
|
assert async_env.action_space == sync_env.action_space
|
|
assert async_env.single_action_space == sync_env.single_action_space
|
|
|
|
async_observations = async_env.reset(seed=0)
|
|
sync_observations = sync_env.reset(seed=0)
|
|
assert np.all(async_observations == sync_observations)
|
|
|
|
for _ in range(num_steps):
|
|
actions = async_env.action_space.sample()
|
|
assert actions in sync_env.action_space
|
|
|
|
# fmt: off
|
|
async_observations, async_rewards, async_dones, async_infos = async_env.step(actions)
|
|
sync_observations, sync_rewards, sync_dones, sync_infos = sync_env.step(actions)
|
|
# fmt: on
|
|
|
|
for idx in range(len(sync_dones)):
|
|
if sync_dones[idx]:
|
|
assert "terminal_observation" in async_infos[idx]
|
|
assert "terminal_observation" in sync_infos[idx]
|
|
assert sync_dones[idx]
|
|
|
|
assert np.all(async_observations == sync_observations)
|
|
assert np.all(async_rewards == sync_rewards)
|
|
assert np.all(async_dones == sync_dones)
|
|
|
|
finally:
|
|
async_env.close()
|
|
sync_env.close()
|
|
|
|
|
|
def test_custom_space_vector_env():
|
|
env = VectorEnv(4, CustomSpace(), CustomSpace())
|
|
|
|
assert isinstance(env.single_observation_space, CustomSpace)
|
|
assert isinstance(env.observation_space, Tuple)
|
|
|
|
assert isinstance(env.single_action_space, CustomSpace)
|
|
assert isinstance(env.action_space, Tuple)
|