mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-01 22:11:25 +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
39 lines
1.0 KiB
Python
39 lines
1.0 KiB
Python
from typing import Optional
|
|
|
|
import gym
|
|
import numpy as np
|
|
import pytest
|
|
from gym.spaces import Box, Dict, Discrete
|
|
|
|
from gym.utils.env_checker import check_env
|
|
|
|
|
|
class ActionDictTestEnv(gym.Env):
|
|
action_space = Dict({"position": Discrete(1), "velocity": Discrete(1)})
|
|
observation_space = Box(low=-1.0, high=2.0, shape=(3,), dtype=np.float32)
|
|
|
|
def step(self, action):
|
|
observation = np.array([1.0, 1.5, 0.5])
|
|
reward = 1
|
|
done = True
|
|
return observation, reward, done
|
|
|
|
def reset(self, seed: Optional[int] = None):
|
|
super().reset(seed=seed)
|
|
return np.array([1.0, 1.5, 0.5])
|
|
|
|
def render(self, mode="human"):
|
|
pass
|
|
|
|
|
|
def test_check_env_dict_action():
|
|
# Environment.step() only returns 3 values: obs, reward, done. Not info!
|
|
test_env = ActionDictTestEnv()
|
|
|
|
with pytest.raises(AssertionError) as errorinfo:
|
|
check_env(env=test_env, warn=True)
|
|
assert (
|
|
str(errorinfo.value)
|
|
== "The `step()` method must return four values: obs, reward, done, info"
|
|
)
|