Prepare Release v2.0 (#192)

docs/misc/changelog.rst

@@ -3,7 +3,7 @@
 Changelog
 ==========
 
-Release 2.0.0a13 (WIP)
+Release 2.0.0 (2023-06-22)
 --------------------------
 
 **Gymnasium support**

pyproject.toml

@@ -4,8 +4,13 @@ line-length = 127
 # Assume Python 3.7
 target-version = "py37"
 select = ["E", "F", "B", "UP", "C90", "RUF"]
-# Ignore explicit stacklevel`
-ignore = ["B028"]
+# B028: Ignore explicit stacklevel`
+# RUF013: Too many false positives (implicit optional)
+ignore = ["B028", "RUF013"]
+
+[tool.ruff.per-file-ignores]
+# ClassVar, implicit optional check not needed for tests
+"./tests/*.py"= ["RUF012", "RUF013"]
 
 [tool.ruff.mccabe]
 # Unlike Flake8, ruff default to a complexity level of 10.

sb3_contrib/ars/ars.py

@@ -3,7 +3,7 @@
 import time
 import warnings
 from functools import partial
-from typing import Any, Dict, Optional, Type, TypeVar, Union
+from typing import Any, ClassVar, Dict, Optional, Type, TypeVar, Union
 
 import numpy as np
 import torch as th
@@ -50,7 +50,7 @@ class ARS(BaseAlgorithm):
     :param _init_setup_model: Whether or not to build the network at the creation of the instance
     """
 
-    policy_aliases: Dict[str, Type[BasePolicy]] = {
+    policy_aliases: ClassVar[Dict[str, Type[BasePolicy]]] = {
         "MlpPolicy": MlpPolicy,
         "LinearPolicy": LinearPolicy,
     }

sb3_contrib/ppo_mask/ppo_mask.py

@@ -1,7 +1,7 @@
 import sys
 import time
 from collections import deque
-from typing import Any, Dict, Optional, Tuple, Type, TypeVar, Union
+from typing import Any, ClassVar, Dict, Optional, Tuple, Type, TypeVar, Union
 
 import numpy as np
 import torch as th
@@ -69,7 +69,7 @@ class MaskablePPO(OnPolicyAlgorithm):
     :param _init_setup_model: Whether or not to build the network at the creation of the instance
     """
 
-    policy_aliases: Dict[str, Type[BasePolicy]] = {
+    policy_aliases: ClassVar[Dict[str, Type[BasePolicy]]] = {
         "MlpPolicy": MlpPolicy,
         "CnnPolicy": CnnPolicy,
         "MultiInputPolicy": MultiInputPolicy,

sb3_contrib/ppo_recurrent/ppo_recurrent.py

@@ -1,7 +1,7 @@
 import sys
 import time
 from copy import deepcopy
-from typing import Any, Dict, Optional, Type, TypeVar, Union
+from typing import Any, ClassVar, Dict, Optional, Type, TypeVar, Union
 
 import numpy as np
 import torch as th
@@ -67,7 +67,7 @@ class RecurrentPPO(OnPolicyAlgorithm):
     :param _init_setup_model: Whether or not to build the network at the creation of the instance
     """
 
-    policy_aliases: Dict[str, Type[BasePolicy]] = {
+    policy_aliases: ClassVar[Dict[str, Type[BasePolicy]]] = {
         "MlpLstmPolicy": MlpLstmPolicy,
         "CnnLstmPolicy": CnnLstmPolicy,
         "MultiInputLstmPolicy": MultiInputLstmPolicy,

sb3_contrib/qrdqn/qrdqn.py

@@ -1,5 +1,5 @@
 import warnings
-from typing import Any, Dict, List, Optional, Tuple, Type, TypeVar, Union
+from typing import Any, ClassVar, Dict, List, Optional, Tuple, Type, TypeVar, Union
 
 import numpy as np
 import torch as th
@@ -60,7 +60,7 @@ class QRDQN(OffPolicyAlgorithm):
     :param _init_setup_model: Whether or not to build the network at the creation of the instance
     """
 
-    policy_aliases: Dict[str, Type[BasePolicy]] = {
+    policy_aliases: ClassVar[Dict[str, Type[BasePolicy]]] = {
         "MlpPolicy": MlpPolicy,
         "CnnPolicy": CnnPolicy,
         "MultiInputPolicy": MultiInputPolicy,

sb3_contrib/tqc/tqc.py

@@ -1,4 +1,4 @@
-from typing import Any, Callable, Dict, List, Optional, Tuple, Type, TypeVar, Union
+from typing import Any, Callable, ClassVar, Dict, List, Optional, Tuple, Type, TypeVar, Union
 
 import numpy as np
 import torch as th
@@ -68,7 +68,7 @@ class TQC(OffPolicyAlgorithm):
     :param _init_setup_model: Whether or not to build the network at the creation of the instance
     """
 
-    policy_aliases: Dict[str, Type[BasePolicy]] = {
+    policy_aliases: ClassVar[Dict[str, Type[BasePolicy]]] = {
         "MlpPolicy": MlpPolicy,
         "CnnPolicy": CnnPolicy,
         "MultiInputPolicy": MultiInputPolicy,

sb3_contrib/trpo/trpo.py

@@ -1,7 +1,7 @@
 import copy
 import warnings
 from functools import partial
-from typing import Any, Dict, List, Optional, Tuple, Type, TypeVar, Union
+from typing import Any, ClassVar, Dict, List, Optional, Tuple, Type, TypeVar, Union
 
 import numpy as np
 import torch as th
@@ -69,7 +69,7 @@ class TRPO(OnPolicyAlgorithm):
     :param _init_setup_model: Whether or not to build the network at the creation of the instance
     """
 
-    policy_aliases: Dict[str, Type[BasePolicy]] = {
+    policy_aliases: ClassVar[Dict[str, Type[BasePolicy]]] = {
         "MlpPolicy": MlpPolicy,
         "CnnPolicy": CnnPolicy,
         "MultiInputPolicy": MultiInputPolicy,

sb3_contrib/version.txt

@@ -1 +1 @@
-2.0.0a13
+2.0.0

setup.py

@@ -65,7 +65,7 @@
     packages=[package for package in find_packages() if package.startswith("sb3_contrib")],
     package_data={"sb3_contrib": ["py.typed", "version.txt"]},
     install_requires=[
-        "stable_baselines3>=2.0.0a13",
+        "stable_baselines3>=2.0.0",
     ],
     description="Contrib package of Stable Baselines3, experimental code.",
     author="Antonin Raffin",
@@ -82,8 +82,10 @@
     project_urls={
         "Code": "https://github.com/Stable-Baselines-Team/stable-baselines3-contrib",
         "Documentation": "https://sb3-contrib.readthedocs.io/",
+        "Changelog": "https://stable-baselines3.readthedocs.io/en/master/misc/changelog.html",
         "Stable-Baselines3": "https://github.com/DLR-RM/stable-baselines3",
         "RL-Zoo": "https://github.com/DLR-RM/rl-baselines3-zoo",
+        "SBX": "https://github.com/araffin/sbx",
     },
     classifiers=[
         "Programming Language :: Python :: 3",