chore(deps): migrate from gym to gymnasium

pyproject.toml

@@ -45,7 +45,7 @@ dependencies = [
   "pymongo",
   "loguru",
   "lightgbm",
-  "gym",
+  "gymnasium<=0.26.2",
   "cvxpy",
   "joblib",
   "matplotlib",

qlib/rl/interpreter.py

@@ -5,9 +5,9 @@
 
 from typing import Any, Generic, TypeVar
 
-import gym
+import gymnasium as gym
 import numpy as np
-from gym import spaces
+from gymnasium import spaces
 
 from qlib.typehint import final
 from .simulator import ActType, StateType

qlib/rl/order_execution/interpreter.py

@@ -8,7 +8,7 @@
 
 import numpy as np
 import pandas as pd
-from gym import spaces
+from gymnasium import spaces
 
 from qlib.constant import EPS
 from qlib.rl.data.base import ProcessedDataProvider

qlib/rl/order_execution/policy.py

@@ -6,11 +6,11 @@
 from pathlib import Path
 from typing import Any, Dict, Generator, Iterable, Optional, OrderedDict, Tuple, cast
 
-import gym
+import gymnasium as gym
 import numpy as np
 import torch
 import torch.nn as nn
-from gym.spaces import Discrete
+from gymnasium.spaces import Discrete
 from tianshou.data import Batch, ReplayBuffer, to_torch
 from tianshou.policy import BasePolicy, PPOPolicy, DQNPolicy
 

qlib/rl/utils/env_wrapper.py

@@ -6,8 +6,8 @@
 import weakref
 from typing import Any, Callable, cast, Dict, Generic, Iterable, Iterator, Optional, Tuple
 
-import gym
-from gym import Space
+import gymnasium as gym
+from gymnasium import Space
 
 from qlib.rl.aux_info import AuxiliaryInfoCollector
 from qlib.rl.interpreter import ActionInterpreter, ObsType, PolicyActType, StateInterpreter

qlib/rl/utils/finite_env.py

@@ -13,7 +13,7 @@
 from contextlib import contextmanager
 from typing import Any, Callable, Dict, Generator, List, Optional, Set, Tuple, Type, Union, cast
 
-import gym
+import gymnasium as gym
 import numpy as np
 from tianshou.env import BaseVectorEnv, DummyVectorEnv, ShmemVectorEnv, SubprocVectorEnv
 

scripts/collect_info.py

@@ -45,7 +45,7 @@ def qlib(self):
             "pymongo",
             "loguru",
             "lightgbm",
-            "gym",
+            "gymnasium",
             "cvxpy",
             "joblib",
             "matplotlib",

tests/rl/test_finite_env.py

@@ -3,7 +3,7 @@
 
 from collections import Counter
 
-import gym
+import gymnasium as gym
 import numpy as np
 from tianshou.data import Batch, Collector
 from tianshou.policy import BasePolicy

tests/rl/test_logger.py

@@ -7,10 +7,10 @@
 import re
 from typing import Any, Tuple
 
-import gym
+import gymnasium as gym
 import numpy as np
 import pandas as pd
-from gym import spaces
+from gymnasium import spaces
 from tianshou.data import Collector, Batch
 from tianshou.policy import BasePolicy
 

tests/rl/test_trainer.py

@@ -7,7 +7,7 @@
 
 import torch
 import torch.nn as nn
-from gym import spaces
+from gymnasium import spaces
 from tianshou.policy import PPOPolicy
 
 from qlib.config import C