Merge 7cbc0ce80a into 0afd5a7385

freqtrade/freqai/RL/Base3ActionRLEnv.py

@@ -1,7 +1,7 @@
 import logging
 from enum import Enum
 
-from gym import spaces
+from gymnasium import spaces
 
 from freqtrade.freqai.RL.BaseEnvironment import BaseEnvironment, Positions
 
@@ -94,9 +94,12 @@ class Base3ActionRLEnv(BaseEnvironment):
 
         observation = self._get_observation()
 
+        #user can play with time if they want
+        truncated = False
+
         self._update_history(info)
 
-        return observation, step_reward, self._done, info
+        return observation, step_reward, self._done,truncated, info
 
     def is_tradesignal(self, action: int) -> bool:
         """

freqtrade/freqai/RL/Base4ActionRLEnv.py

@@ -1,7 +1,7 @@
 import logging
 from enum import Enum
 
-from gym import spaces
+from gymnasium import spaces
 
 from freqtrade.freqai.RL.BaseEnvironment import BaseEnvironment, Positions
 
@@ -96,9 +96,12 @@ class Base4ActionRLEnv(BaseEnvironment):
 
         observation = self._get_observation()
 
+        #user can play with time if they want
+        truncated = False
+
         self._update_history(info)
 
-        return observation, step_reward, self._done, info
+        return observation, step_reward, self._done,truncated, info
 
     def is_tradesignal(self, action: int) -> bool:
         """

freqtrade/freqai/RL/Base5ActionRLEnv.py

@@ -1,7 +1,7 @@
 import logging
 from enum import Enum
 
-from gym import spaces
+from gymnasium import spaces
 
 from freqtrade.freqai.RL.BaseEnvironment import BaseEnvironment, Positions
 
@@ -101,10 +101,12 @@ class Base5ActionRLEnv(BaseEnvironment):
         )
 
         observation = self._get_observation()
+        #user can play with time if they want
+        truncated = False
 
         self._update_history(info)
 
-        return observation, step_reward, self._done, info
+        return observation, step_reward, self._done,truncated, info
 
     def is_tradesignal(self, action: int) -> bool:
         """

freqtrade/freqai/RL/BaseEnvironment.py

@@ -4,11 +4,11 @@ from abc import abstractmethod
 from enum import Enum
 from typing import Optional, Type, Union
 
-import gym
+import gymnasium as gym
 import numpy as np
 import pandas as pd
-from gym import spaces
-from gym.utils import seeding
+from gymnasium import spaces
+from gymnasium.utils import seeding
 from pandas import DataFrame
 
 
@@ -203,7 +203,7 @@ class BaseEnvironment(gym.Env):
         self.close_trade_profit = []
         self._total_unrealized_profit = 1
 
-        return self._get_observation()
+        return self._get_observation(), self.history
 
     @abstractmethod
     def step(self, action: int):

freqtrade/freqai/RL/BaseReinforcementLearningModel.py

@@ -6,7 +6,7 @@ from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any, Callable, Dict, Optional, Tuple, Type, Union
 
-import gym
+import gymnasium as gym
 import numpy as np
 import numpy.typing as npt
 import pandas as pd
@@ -433,7 +433,6 @@ class BaseReinforcementLearningModel(IFreqaiModel):
 
 def make_env(MyRLEnv: Type[gym.Env], env_id: str, rank: int,
              seed: int, train_df: DataFrame, price: DataFrame,
-             monitor: bool = False,
              env_info: Dict[str, Any] = {}) -> Callable:
     """
     Utility function for multiprocessed env.
@@ -450,8 +449,7 @@ def make_env(MyRLEnv: Type[gym.Env], env_id: str, rank: int,
 
         env = MyRLEnv(df=train_df, prices=price, id=env_id, seed=seed + rank,
                       **env_info)
-        if monitor:
-            env = Monitor(env)
+        
         return env
     set_random_seed(seed)
     return _init