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
127 lines
3.2 KiB
Python
127 lines
3.2 KiB
Python
from typing import Optional
|
|
|
|
import numpy as np
|
|
import gym
|
|
import time
|
|
|
|
from gym.spaces import Box, Discrete, MultiDiscrete, MultiBinary, Tuple, Dict
|
|
|
|
spaces = [
|
|
Box(low=np.array(-1.0), high=np.array(1.0), dtype=np.float64),
|
|
Box(low=np.array([0.0]), high=np.array([10.0]), dtype=np.float32),
|
|
Box(
|
|
low=np.array([-1.0, 0.0, 0.0]), high=np.array([1.0, 1.0, 1.0]), dtype=np.float32
|
|
),
|
|
Box(
|
|
low=np.array([[-1.0, 0.0], [0.0, -1.0]]), high=np.ones((2, 2)), dtype=np.float32
|
|
),
|
|
Box(low=0, high=255, shape=(), dtype=np.uint8),
|
|
Box(low=0, high=255, shape=(32, 32, 3), dtype=np.uint8),
|
|
Discrete(2),
|
|
Tuple((Discrete(3), Discrete(5))),
|
|
Tuple(
|
|
(
|
|
Discrete(7),
|
|
Box(low=np.array([0.0, -1.0]), high=np.array([1.0, 1.0]), dtype=np.float32),
|
|
)
|
|
),
|
|
MultiDiscrete([11, 13, 17]),
|
|
MultiBinary(19),
|
|
Dict(
|
|
{
|
|
"position": Discrete(23),
|
|
"velocity": Box(
|
|
low=np.array([0.0]), high=np.array([1.0]), dtype=np.float32
|
|
),
|
|
}
|
|
),
|
|
Dict(
|
|
{
|
|
"position": Dict({"x": Discrete(29), "y": Discrete(31)}),
|
|
"velocity": Tuple(
|
|
(Discrete(37), Box(low=0, high=255, shape=(), dtype=np.uint8))
|
|
),
|
|
}
|
|
),
|
|
]
|
|
|
|
HEIGHT, WIDTH = 64, 64
|
|
|
|
|
|
class UnittestSlowEnv(gym.Env):
|
|
def __init__(self, slow_reset=0.3):
|
|
super(UnittestSlowEnv, self).__init__()
|
|
self.slow_reset = slow_reset
|
|
self.observation_space = Box(
|
|
low=0, high=255, shape=(HEIGHT, WIDTH, 3), dtype=np.uint8
|
|
)
|
|
self.action_space = Box(low=0.0, high=1.0, shape=(), dtype=np.float32)
|
|
|
|
def reset(self, seed: Optional[int] = None):
|
|
super().reset(seed=seed)
|
|
if self.slow_reset > 0:
|
|
time.sleep(self.slow_reset)
|
|
return self.observation_space.sample()
|
|
|
|
def step(self, action):
|
|
time.sleep(action)
|
|
observation = self.observation_space.sample()
|
|
reward, done = 0.0, False
|
|
return observation, reward, done, {}
|
|
|
|
|
|
class CustomSpace(gym.Space):
|
|
"""Minimal custom observation space."""
|
|
|
|
def __eq__(self, other):
|
|
return isinstance(other, CustomSpace)
|
|
|
|
|
|
custom_spaces = [
|
|
CustomSpace(),
|
|
Tuple((CustomSpace(), Box(low=0, high=255, shape=(), dtype=np.uint8))),
|
|
]
|
|
|
|
|
|
class CustomSpaceEnv(gym.Env):
|
|
def __init__(self):
|
|
super(CustomSpaceEnv, self).__init__()
|
|
self.observation_space = CustomSpace()
|
|
self.action_space = CustomSpace()
|
|
|
|
def reset(self, seed: Optional[int] = None):
|
|
super().reset(seed=seed)
|
|
return "reset"
|
|
|
|
def step(self, action):
|
|
observation = "step({0:s})".format(action)
|
|
reward, done = 0.0, False
|
|
return observation, reward, done, {}
|
|
|
|
|
|
def make_env(env_name, seed):
|
|
def _make():
|
|
env = gym.make(env_name)
|
|
env.reset(seed=seed)
|
|
return env
|
|
|
|
return _make
|
|
|
|
|
|
def make_slow_env(slow_reset, seed):
|
|
def _make():
|
|
env = UnittestSlowEnv(slow_reset=slow_reset)
|
|
env.reset(seed=seed)
|
|
return env
|
|
|
|
return _make
|
|
|
|
|
|
def make_custom_space_env(seed):
|
|
def _make():
|
|
env = CustomSpaceEnv()
|
|
env.reset(seed=seed)
|
|
return env
|
|
|
|
return _make
|