From 488739424d07b5902569ef53e9e8a09a9a301718 Mon Sep 17 00:00:00 2001 From: robcaulk Date: Wed, 5 Oct 2022 20:55:50 +0200 Subject: [PATCH] fix reward inconsistency in template --- freqtrade/freqai/RL/BaseReinforcementLearningModel.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/freqtrade/freqai/RL/BaseReinforcementLearningModel.py b/freqtrade/freqai/RL/BaseReinforcementLearningModel.py index 115ee59ce..e89320668 100644 --- a/freqtrade/freqai/RL/BaseReinforcementLearningModel.py +++ b/freqtrade/freqai/RL/BaseReinforcementLearningModel.py @@ -309,7 +309,6 @@ class BaseReinforcementLearningModel(IFreqaiModel): return -2 pnl = self.get_unrealized_profit() - rew = np.sign(pnl) * (pnl + 1) factor = 100. # reward agent for entering trades @@ -340,13 +339,13 @@ class BaseReinforcementLearningModel(IFreqaiModel): if action == Actions.Long_exit.value and self._position == Positions.Long: if pnl > self.profit_aim * self.rr: factor *= self.rl_config['model_reward_parameters'].get('win_reward_factor', 2) - return float(rew * factor) + return float(pnl * factor) # close short if action == Actions.Short_exit.value and self._position == Positions.Short: if pnl > self.profit_aim * self.rr: factor *= self.rl_config['model_reward_parameters'].get('win_reward_factor', 2) - return float(rew * factor) + return float(pnl * factor) return 0.