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

clean RL tests to avoid dir pollution and increase speed

Browse Source
This commit is contained in:
robcaulk
2022-10-08 12:10:38 +02:00
parent 3e258e000e
commit 8d7adfabe9
6 changed files with 43 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
freqtrade/freqai/RL/BaseReinforcementLearningModel.py
View File

@@ -63,6 +63,7 @@ class BaseReinforcementLearningModel(IFreqaiModel):
self.MODELCLASS = getattr(mod, self.model_type)
self.policy_type = self.freqai_info['rl_config']['policy_type']
self.unset_outlier_removal()
self.net_arch = self.rl_config.get('net_arch', [128, 128])
def unset_outlier_removal(self):
"""
@@ -287,6 +288,17 @@ class BaseReinforcementLearningModel(IFreqaiModel):
return model
def _on_stop(self):
"""
Hook called on bot shutdown. Close SubprocVecEnv subprocesses for clean shutdown.
"""
if self.train_env:
self.train_env.close()
if self.eval_env:
self.eval_env.close()
# Nested class which can be overridden by user to customize further
class MyRLEnv(Base5ActionRLEnv):
"""

2
freqtrade/freqai/prediction_models/ReinforcementLearner.py
View File

@@ -31,7 +31,7 @@ class ReinforcementLearner(BaseReinforcementLearningModel):
total_timesteps = self.freqai_info["rl_config"]["train_cycles"] * len(train_df)
policy_kwargs = dict(activation_fn=th.nn.ReLU,
net_arch=[128, 128])
net_arch=self.net_arch)
if dk.pair not in self.dd.model_dictionary or not self.continual_learning:
model = self.MODELCLASS(self.policy_type, self.train_env, policy_kwargs=policy_kwargs,

13
freqtrade/freqai/prediction_models/ReinforcementLearner_multiproc.py
View File

@@ -28,7 +28,7 @@ class ReinforcementLearner_multiproc(BaseReinforcementLearningModel):
# model arch
policy_kwargs = dict(activation_fn=th.nn.ReLU,
net_arch=[128, 128])
net_arch=self.net_arch)
if dk.pair not in self.dd.model_dictionary or not self.continual_learning:
model = self.MODELCLASS(self.policy_type, self.train_env, policy_kwargs=policy_kwargs,
@@ -87,14 +87,3 @@ class ReinforcementLearner_multiproc(BaseReinforcementLearningModel):
self.eval_callback = EvalCallback(self.eval_env, deterministic=True,
render=False, eval_freq=len(train_df),
best_model_save_path=str(dk.data_path))
def _on_stop(self):
"""
Hook called on bot shutdown. Close SubprocVecEnv subprocesses for clean shutdown.
"""
if self.train_env:
self.train_env.close()
if self.eval_env:
self.eval_env.close()