gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 19:50:17 +01:00
Code Issues Projects Releases Wiki Activity

Batch RL Tutorial (#372)

Browse Source
This commit is contained in:
Gal Leibovich
2019-07-14 18:43:48 +03:00
committed by GitHub
parent b82414138d
commit 19ad2d60a7
40 changed files with 1155 additions and 182 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rl_coach/architectures/tensorflow_components/heads/cil_head.py
View File

@@ -27,7 +27,7 @@ from rl_coach.utils import force_list
class RegressionHead(Head):
def __init__(self, agent_parameters: AgentParameters, spaces: SpacesDefinition, network_name: str,
head_idx: int = 0, loss_weight: float = 1., is_local: bool = True, activation_function: str='relu',
dense_layer=Dense, scheme=[Dense(256), Dense(256)]):
dense_layer=Dense, scheme=[Dense(256), Dense(256)], output_bias_initializer=None):
super().__init__(agent_parameters, spaces, network_name, head_idx, loss_weight, is_local, activation_function,
dense_layer=dense_layer)
self.name = 'regression_head'
@@ -42,6 +42,7 @@ class RegressionHead(Head):
self.loss_type = tf.losses.huber_loss
else:
self.loss_type = tf.losses.mean_squared_error
self.output_bias_initializer = output_bias_initializer
def _build_module(self, input_layer):
self.layers.append(input_layer)
@@ -50,7 +51,8 @@ class RegressionHead(Head):
layer_params(input_layer=self.layers[-1], name='{}_{}'.format(layer_params.__class__.__name__, idx))
))
self.layers.append(self.dense_layer(self.num_actions)(self.layers[-1], name='output'))
self.layers.append(self.dense_layer(self.num_actions)(self.layers[-1], name='output',
bias_initializer=self.output_bias_initializer))
self.output = self.layers[-1]
def __str__(self):