stable-baselines3/stable_baselines3/common/env_util.py
Antonin RAFFIN 40e0b9d2c8
Add Gymnasium support (#1327)
* Fix failing set_env test

* Fix test failiing due to deprectation of env.seed

* Adjust mean reward threshold in failing test

* Fix her test failing due to rng

* Change seed and revert reward threshold to 90

* Pin gym version

* Make VecEnv compatible with gym seeding change

* Revert change to VecEnv reset signature

* Change subprocenv seed cmd to call reset instead

* Fix type check

* Add backward compat

* Add `compat_gym_seed` helper

* Add goal env checks in env_checker

* Add docs on  HER requirements for envs

* Capture user warning in test with inverted box space

* Update ale-py version

* Fix randint

* Allow noop_max to be zero

* Update changelog

* Update docker image

* Update doc conda env and dockerfile

* Custom envs should not have any warnings

* Fix test for numpy >= 1.21

* Add check for vectorized compute reward

* Bump to gym 0.24

* Fix gym default step docstring

* Test downgrading gym

* Revert "Test downgrading gym"

This reverts commit 0072b77156c006ada8a1d6e26ce347ed85a83eeb.

* Fix protobuf error

* Fix in dependencies

* Fix protobuf dep

* Use newest version of cartpole

* Update gym

* Fix warning

* Loosen required scipy version

* Scipy no longer needed

* Try gym 0.25

* Silence warnings from gym

* Filter warnings during tests

* Update doc

* Update requirements

* Add gym 26 compat in vec env

* Fixes in envs and tests for gym 0.26+

* Enforce gym 0.26 api

* format

* Fix formatting

* Fix dependencies

* Fix syntax

* Cleanup doc and warnings

* Faster tests

* Higher budget for HER perf test (revert prev change)

* Fixes and update doc

* Fix doc build

* Fix breaking change

* Fixes for rendering

* Rename variables in monitor

* update render method for gym 0.26 API

backwards compatible (mode argument is allowed) while using the gym 0.26 API (render mode is determined at environment creation)

* update tests and docs to new gym render API

* undo removal of render modes metatadata check

* set rgb_array as default render mode for gym.make

* undo changes & raise warning if not 'rgb_array'

* Fix type check

* Remove recursion and fix type checking

* Remove hacks for protobuf and gym 0.24

* Fix type annotations

* reuse existing render_mode attribute

* return tiled images for 'human' render mode

* Allow to use opencv for human render, fix typos

* Add warning when using non-zero start with Discrete (fixes #1197)

* Fix type checking

* Bug fixes and handle more cases

* Throw proper warnings

* Update test

* Fix new metadata name

* Ignore numpy warnings

* Fixes in vec recorder

* Global ignore

* Filter local warning too

* Monkey patch not needed for gym 26

* Add doc of VecEnv vs Gym API

* Add render test

* Fix return type

* Update VecEnv vs Gym API doc

* Fix for custom render mode

* Fix return type

* Fix type checking

* check test env test_buffer

* skip render check

* check env test_dict_env

* test_env test_gae

* check envs in remaining tests

* Update tests

* Add warning for Discrete action space with non-zero (#1295)

* Fix atari annotation

* ignore get_action_meanings [attr-defined]

* Fix mypy issues

* Add patch for gym/gymnasium transition

* Switch to gymnasium

* Rely on signature instead of version

* More patches

* Type ignore because of https://github.com/Farama-Foundation/Gymnasium/pull/39

* Fix doc build

* Fix pytype errors

* Fix atari requirement

* Update env checker due to change in dtype for Discrete

* Fix type hint

* Convert spaces for saved models

* Ignore pytype

* Remove gitlab CI

* Disable pytype for convert space

* Fix undefined info

* Fix undefined info

* Upgrade shimmy

* Fix wrappers type annotation (need PR from Gymnasium)

* Fix gymnasium dependency

* Fix dependency declaration

* Cap pygame version for python 3.7

* Point to master branch (v0.28.0)

* Fix: use main not master branch

* Rename done to terminated

* Fix pygame dependency for python 3.7

* Rename gym to gymnasium

* Update Gymnasium

* Fix test

* Fix tests

* Forks don't have access to private variables

* Fix linter warnings

* Update read the doc env

* Fix env checker for GoalEnv

* Fix import

* Update env checker (more info) and fix dtype

* Use micromamab for Docker

* Update dependencies

* Clarify VecEnv doc

* Fix Gymnasium version

* Copy file only after mamba install

* [ci skip] Update docker doc

* Polish code

* Reformat

* Remove deprecated features

* Ignore warning

* Update doc

* Update examples and changelog

* Fix type annotation bundle (SAC, TD3, A2C, PPO, base class) (#1436)

* Fix SAC type hints, improve DQN ones

* Fix A2C and TD3 type hints

* Fix PPO type hints

* Fix on-policy type hints

* Fix base class type annotation, do not use defaults

* Update version

* Disable mypy for python 3.7

* Rename Gym26StepReturn

* Update continuous critic type annotation

* Fix pytype complain

---------

Co-authored-by: Carlos Luis <carlos.luisgonc@gmail.com>
Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Co-authored-by: Thomas Lips <37955681+tlpss@users.noreply.github.com>
Co-authored-by: tlips <thomas.lips@ugent.be>
Co-authored-by: tlpss <thomas17.lips@gmail.com>
Co-authored-by: Quentin GALLOUÉDEC <gallouedec.quentin@gmail.com>
2023-04-14 13:13:59 +02:00

170 lines
7.4 KiB
Python

import os
from typing import Any, Callable, Dict, Optional, Type, Union
import gymnasium as gym
from stable_baselines3.common.atari_wrappers import AtariWrapper
from stable_baselines3.common.monitor import Monitor
from stable_baselines3.common.utils import compat_gym_seed
from stable_baselines3.common.vec_env import DummyVecEnv, SubprocVecEnv, VecEnv
from stable_baselines3.common.vec_env.patch_gym import _patch_env
def unwrap_wrapper(env: gym.Env, wrapper_class: Type[gym.Wrapper]) -> Optional[gym.Wrapper]:
"""
Retrieve a ``VecEnvWrapper`` object by recursively searching.
:param env: Environment to unwrap
:param wrapper_class: Wrapper to look for
:return: Environment unwrapped till ``wrapper_class`` if it has been wrapped with it
"""
env_tmp = env
while isinstance(env_tmp, gym.Wrapper):
if isinstance(env_tmp, wrapper_class):
return env_tmp
env_tmp = env_tmp.env
return None
def is_wrapped(env: gym.Env, wrapper_class: Type[gym.Wrapper]) -> bool:
"""
Check if a given environment has been wrapped with a given wrapper.
:param env: Environment to check
:param wrapper_class: Wrapper class to look for
:return: True if environment has been wrapped with ``wrapper_class``.
"""
return unwrap_wrapper(env, wrapper_class) is not None
def make_vec_env(
env_id: Union[str, Callable[..., gym.Env]],
n_envs: int = 1,
seed: Optional[int] = None,
start_index: int = 0,
monitor_dir: Optional[str] = None,
wrapper_class: Optional[Callable[[gym.Env], gym.Env]] = None,
env_kwargs: Optional[Dict[str, Any]] = None,
vec_env_cls: Optional[Type[Union[DummyVecEnv, SubprocVecEnv]]] = None,
vec_env_kwargs: Optional[Dict[str, Any]] = None,
monitor_kwargs: Optional[Dict[str, Any]] = None,
wrapper_kwargs: Optional[Dict[str, Any]] = None,
) -> VecEnv:
"""
Create a wrapped, monitored ``VecEnv``.
By default it uses a ``DummyVecEnv`` which is usually faster
than a ``SubprocVecEnv``.
:param env_id: either the env ID, the env class or a callable returning an env
:param n_envs: the number of environments you wish to have in parallel
:param seed: the initial seed for the random number generator
:param start_index: start rank index
:param monitor_dir: Path to a folder where the monitor files will be saved.
If None, no file will be written, however, the env will still be wrapped
in a Monitor wrapper to provide additional information about training.
:param wrapper_class: Additional wrapper to use on the environment.
This can also be a function with single argument that wraps the environment in many things.
Note: the wrapper specified by this parameter will be applied after the ``Monitor`` wrapper.
if some cases (e.g. with TimeLimit wrapper) this can lead to undesired behavior.
See here for more details: https://github.com/DLR-RM/stable-baselines3/issues/894
:param env_kwargs: Optional keyword argument to pass to the env constructor
:param vec_env_cls: A custom ``VecEnv`` class constructor. Default: None.
:param vec_env_kwargs: Keyword arguments to pass to the ``VecEnv`` class constructor.
:param monitor_kwargs: Keyword arguments to pass to the ``Monitor`` class constructor.
:param wrapper_kwargs: Keyword arguments to pass to the ``Wrapper`` class constructor.
:return: The wrapped environment
"""
env_kwargs = env_kwargs or {}
vec_env_kwargs = vec_env_kwargs or {}
monitor_kwargs = monitor_kwargs or {}
wrapper_kwargs = wrapper_kwargs or {}
assert vec_env_kwargs is not None # for mypy
def make_env(rank: int) -> Callable[[], gym.Env]:
def _init() -> gym.Env:
# For type checker:
assert monitor_kwargs is not None
assert wrapper_kwargs is not None
assert env_kwargs is not None
if isinstance(env_id, str):
# if the render mode was not specified, we set it to `rgb_array` as default.
kwargs = {"render_mode": "rgb_array"}
kwargs.update(env_kwargs)
try:
env = gym.make(env_id, **kwargs) # type: ignore[arg-type]
except TypeError:
env = gym.make(env_id, **env_kwargs)
else:
env = env_id(**env_kwargs)
# Patch to support gym 0.21/0.26 and gymnasium
env = _patch_env(env)
if seed is not None:
compat_gym_seed(env, seed=seed + rank)
env.action_space.seed(seed + rank)
# Wrap the env in a Monitor wrapper
# to have additional training information
monitor_path = os.path.join(monitor_dir, str(rank)) if monitor_dir is not None else None
# Create the monitor folder if needed
if monitor_path is not None and monitor_dir is not None:
os.makedirs(monitor_dir, exist_ok=True)
env = Monitor(env, filename=monitor_path, **monitor_kwargs)
# Optionally, wrap the environment with the provided wrapper
if wrapper_class is not None:
env = wrapper_class(env, **wrapper_kwargs)
return env
return _init
# No custom VecEnv is passed
if vec_env_cls is None:
# Default: use a DummyVecEnv
vec_env_cls = DummyVecEnv
return vec_env_cls([make_env(i + start_index) for i in range(n_envs)], **vec_env_kwargs)
def make_atari_env(
env_id: Union[str, Callable[..., gym.Env]],
n_envs: int = 1,
seed: Optional[int] = None,
start_index: int = 0,
monitor_dir: Optional[str] = None,
wrapper_kwargs: Optional[Dict[str, Any]] = None,
env_kwargs: Optional[Dict[str, Any]] = None,
vec_env_cls: Optional[Union[Type[DummyVecEnv], Type[SubprocVecEnv]]] = None,
vec_env_kwargs: Optional[Dict[str, Any]] = None,
monitor_kwargs: Optional[Dict[str, Any]] = None,
) -> VecEnv:
"""
Create a wrapped, monitored VecEnv for Atari.
It is a wrapper around ``make_vec_env`` that includes common preprocessing for Atari games.
:param env_id: either the env ID, the env class or a callable returning an env
:param n_envs: the number of environments you wish to have in parallel
:param seed: the initial seed for the random number generator
:param start_index: start rank index
:param monitor_dir: Path to a folder where the monitor files will be saved.
If None, no file will be written, however, the env will still be wrapped
in a Monitor wrapper to provide additional information about training.
:param wrapper_kwargs: Optional keyword argument to pass to the ``AtariWrapper``
:param env_kwargs: Optional keyword argument to pass to the env constructor
:param vec_env_cls: A custom ``VecEnv`` class constructor. Default: None.
:param vec_env_kwargs: Keyword arguments to pass to the ``VecEnv`` class constructor.
:param monitor_kwargs: Keyword arguments to pass to the ``Monitor`` class constructor.
:return: The wrapped environment
"""
return make_vec_env(
env_id,
n_envs=n_envs,
seed=seed,
start_index=start_index,
monitor_dir=monitor_dir,
wrapper_class=AtariWrapper,
env_kwargs=env_kwargs,
vec_env_cls=vec_env_cls,
vec_env_kwargs=vec_env_kwargs,
monitor_kwargs=monitor_kwargs,
wrapper_kwargs=wrapper_kwargs,
)