From d03fe1f8eee09a5f4e6aa936bceb50e4dc983c04 Mon Sep 17 00:00:00 2001
From: Richard Jozsa <38407205+richardjozsa@users.noreply.github.com>
Date: Thu, 16 Mar 2023 00:53:37 +0100
Subject: [PATCH] add latest experimental version of gymnasium

---
 freqtrade/freqai/RL/Base3ActionRLEnv.py               | 7 +++++--
 freqtrade/freqai/RL/Base4ActionRLEnv.py               | 7 +++++--
 freqtrade/freqai/RL/Base5ActionRLEnv.py               | 6 ++++--
 freqtrade/freqai/RL/BaseEnvironment.py                | 8 ++++----
 freqtrade/freqai/RL/BaseReinforcementLearningModel.py | 2 +-
 requirements-freqai-rl.txt                            | 8 +++++---
 6 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/freqtrade/freqai/RL/Base3ActionRLEnv.py b/freqtrade/freqai/RL/Base3ActionRLEnv.py
index 3b5fffc58..83682263b 100644
--- a/freqtrade/freqai/RL/Base3ActionRLEnv.py
+++ b/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:
         """
diff --git a/freqtrade/freqai/RL/Base4ActionRLEnv.py b/freqtrade/freqai/RL/Base4ActionRLEnv.py
index 8f45028b1..b26ba988a 100644
--- a/freqtrade/freqai/RL/Base4ActionRLEnv.py
+++ b/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
 
@@ -106,9 +106,12 @@ 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:
         """
diff --git a/freqtrade/freqai/RL/Base5ActionRLEnv.py b/freqtrade/freqai/RL/Base5ActionRLEnv.py
index 22d3cae30..6ce598dfb 100644
--- a/freqtrade/freqai/RL/Base5ActionRLEnv.py
+++ b/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
 
@@ -111,10 +111,12 @@ 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:
         """
diff --git a/freqtrade/freqai/RL/BaseEnvironment.py b/freqtrade/freqai/RL/BaseEnvironment.py
index 7a4467bf7..60b65cc03 100644
--- a/freqtrade/freqai/RL/BaseEnvironment.py
+++ b/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
 
 
@@ -195,7 +195,7 @@ 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):
diff --git a/freqtrade/freqai/RL/BaseReinforcementLearningModel.py b/freqtrade/freqai/RL/BaseReinforcementLearningModel.py
index e10880f46..e18419d75 100644
--- a/freqtrade/freqai/RL/BaseReinforcementLearningModel.py
+++ b/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
diff --git a/requirements-freqai-rl.txt b/requirements-freqai-rl.txt
index 4de7d8fab..233876425 100644
--- a/requirements-freqai-rl.txt
+++ b/requirements-freqai-rl.txt
@@ -3,8 +3,10 @@
 
 # Required for freqai-rl
 torch==1.13.1; python_version < '3.11'
-stable-baselines3==1.7.0; python_version < '3.11'
-sb3-contrib==1.7.0; python_version < '3.11'
+#until these branches will be released we can use this
+git+https://github.com/Farama-Foundation/Gymnasium@main
+git+https://github.com/DLR-RM/stable-baselines3@feat/gymnasium-support
+git+https://github.com/Stable-Baselines-Team/stable-baselines3-contrib@feat/gymnasium-support
 # Gym is forced to this version by stable-baselines3.
 setuptools==65.5.1 # Should be removed when gym is fixed.
-gym==0.21; python_version < '3.11'
+