Fix env.reset() to return (obs, info) tuple for SB3 v2.0+ compatibility

README.md

@@ -75,7 +75,7 @@ Key contributors include:
 
 - [**Hongyang (Bruce) Yang**](https://www.linkedin.com/in/brucehy/) – research and development on financial reinforcement learning frameworks, market environments, and quantitative trading applications
 - [other contributors…]
-  
+
 ## Overview
 
 FinRL has three layers: market environments, agents, and applications.  For a trading task (on the top), an agent (in the middle) interacts with a market environment (at the bottom), making sequential decisions.

finrl/meta/env_cryptocurrency_trading/env_btc_ccxt.py

@@ -81,7 +81,7 @@ def reset(
                 self.stocks * 2**-4,
             )
         ).astype(np.float32)
-        return state
+        return state, {}
 
     def step(self, action) -> (np.ndarray, float, bool, None):
         stock_action = action[0]

finrl/meta/env_cryptocurrency_trading/env_multiple_crypto.py

@@ -60,7 +60,7 @@ def reset(
         self.total_asset = self.cash + (self.stocks * self.price_array[self.time]).sum()
 
         state = self.get_state()
-        return state
+        return state, {}
 
     def step(self, actions) -> (np.ndarray, float, bool, None):
         self.time += 1
@@ -106,7 +106,7 @@ def get_state(self):
             tech_i = self.tech_array[self.time - i]
             normalized_tech_i = tech_i * 2**-15
             state = np.hstack((state, normalized_tech_i)).astype(np.float32)
-        return state
+        return state, {}
 
     def close(self):
         pass

finrl/meta/env_stock_trading/env_stocktrading_cashpenalty.py

@@ -160,7 +160,7 @@ def reset(
             + self.get_date_vector(self.date_index)
         )
         self.state_memory.append(init_state)
-        return init_state
+        return init_state, {}
 
     def get_date_vector(self, date, cols=None):
         if (cols is None) and (self.cached_data is not None):

finrl/meta/env_stock_trading/env_stocktrading_stoploss.py

@@ -167,7 +167,7 @@ def reset(
             + self.get_date_vector(self.date_index)
         )
         self.state_memory.append(init_state)
-        return init_state
+        return init_state, {}
 
     def get_date_vector(self, date, cols=None):
         if (cols is None) and (self.cached_data is not None):