adelorenzo/stable
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ensure normalization acceleration methods are employed in RL

Browse Source
This commit is contained in:
robcaulk
2022-11-12 12:01:59 +01:00
parent 6746868ea7
commit 9c6b97c678
2 changed files with 24 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
docs/freqai-reinforcement-learning.md
View File

@@ -38,8 +38,6 @@ where `ReinforcementLearner` will use the templated `ReinforcementLearner` from
self, pair, df, tf, informative=None, set_generalized_indicators=False self, pair, df, tf, informative=None, set_generalized_indicators=False
): ):
coin = pair.split('/')[0]
if informative is None: if informative is None:
informative = self.dp.get_pair_dataframe(pair, tf) informative = self.dp.get_pair_dataframe(pair, tf)
@@ -47,15 +45,15 @@ where `ReinforcementLearner` will use the templated `ReinforcementLearner` from
for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]: for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
t = int(t) t = int(t)
informative[f"%-{coin}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t) informative[f"%-{pair}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
informative[f"%-{coin}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t) informative[f"%-{pair}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
informative[f"%-{coin}adx-period_{t}"] = ta.ADX(informative, window=t) informative[f"%-{pair}adx-period_{t}"] = ta.ADX(informative, window=t)
# The following features are necessary for RL models # The following features are necessary for RL models
informative[f"%-{coin}raw_close"] = informative["close"] informative[f"%-{pair}raw_close"] = informative["close"]
informative[f"%-{coin}raw_open"] = informative["open"] informative[f"%-{pair}raw_open"] = informative["open"]
informative[f"%-{coin}raw_high"] = informative["high"] informative[f"%-{pair}raw_high"] = informative["high"]
informative[f"%-{coin}raw_low"] = informative["low"] informative[f"%-{pair}raw_low"] = informative["low"]
indicators = [col for col in informative if col.startswith("%")] indicators = [col for col in informative if col.startswith("%")]
# This loop duplicates and shifts all indicators to add a sense of recency to data # This loop duplicates and shifts all indicators to add a sense of recency to data
@@ -88,10 +86,10 @@ Most of the function remains the same as for typical Regressors, however, the fu
```python ```python
# The following features are necessary for RL models # The following features are necessary for RL models
informative[f"%-{coin}raw_close"] = informative["close"] informative[f"%-{pair}raw_close"] = informative["close"]
informative[f"%-{coin}raw_open"] = informative["open"] informative[f"%-{pair}raw_open"] = informative["open"]
informative[f"%-{coin}raw_high"] = informative["high"] informative[f"%-{pair}raw_high"] = informative["high"]
informative[f"%-{coin}raw_low"] = informative["low"] informative[f"%-{pair}raw_low"] = informative["low"]
``` ```
Finally, there is no explicit "label" to make - instead the you need to assign the `&-action` column which will contain the agent's actions when accessed in `populate_entry/exit_trends()`. In the present example, the user set the neutral action to 0. This value should align with the environment used. FreqAI provides two environments, both use 0 as the neutral action. Finally, there is no explicit "label" to make - instead the you need to assign the `&-action` column which will contain the agent's actions when accessed in `populate_entry/exit_trends()`. In the present example, the user set the neutral action to 0. This value should align with the environment used. FreqAI provides two environments, both use 0 as the neutral action.

18
freqtrade/freqai/RL/BaseReinforcementLearningModel.py
View File

@@ -253,18 +253,26 @@ class BaseReinforcementLearningModel(IFreqaiModel):
Builds the train prices and test prices for the environment. Builds the train prices and test prices for the environment.
""" """
coin = pair.split('/')[0] pair = pair.replace(':', '')
train_df = data_dictionary["train_features"] train_df = data_dictionary["train_features"]
test_df = data_dictionary["test_features"] test_df = data_dictionary["test_features"]
# price data for model training and evaluation # price data for model training and evaluation
tf = self.config['timeframe'] tf = self.config['timeframe']
ohlc_list = [f'%-{coin}raw_open_{tf}', f'%-{coin}raw_low_{tf}', ohlc_list = [f'%-{pair}raw_open_{tf}', f'%-{pair}raw_low_{tf}',
f'%-{coin}raw_high_{tf}', f'%-{coin}raw_close_{tf}'] f'%-{pair}raw_high_{tf}', f'%-{pair}raw_close_{tf}']
rename_dict = {f'%-{coin}raw_open_{tf}': 'open', f'%-{coin}raw_low_{tf}': 'low', rename_dict = {f'%-{pair}raw_open_{tf}': 'open', f'%-{pair}raw_low_{tf}': 'low',
f'%-{coin}raw_high_{tf}': ' high', f'%-{coin}raw_close_{tf}': 'close'} f'%-{pair}raw_high_{tf}': ' high', f'%-{pair}raw_close_{tf}': 'close'}
prices_train = train_df.filter(ohlc_list, axis=1) prices_train = train_df.filter(ohlc_list, axis=1)
if prices_train.empty:
raise OperationalException('Reinforcement learning module didnt find the raw prices '
'assigned in populate_any_indicators. Please assign them '
'with:\n'
'informative[f"%-{pair}raw_close"] = informative["close"]\n'
'informative[f"%-{pair}raw_open"] = informative["open"]\n'
'informative[f"%-{pair}raw_high"] = informative["high"]\n'
'informative[f"%-{pair}raw_low"] = informative["low"]\n')
prices_train.rename(columns=rename_dict, inplace=True) prices_train.rename(columns=rename_dict, inplace=True)
prices_train.reset_index(drop=True) prices_train.reset_index(drop=True)