gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 11:40:18 +01:00
Code Issues Projects Releases Wiki Activity

load and save function for non-episodic replay buffers + carla improvements + network bug fixes

Browse Source
This commit is contained in:
itaicaspi-intel
2018-09-06 16:46:57 +03:00
parent d59a700248
commit a9bd1047c4
8 changed files with 50 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rl_coach/architectures/tensorflow_components/heads/head.py
View File

@@ -59,8 +59,8 @@ class Head(object):
self.loss = []
self.loss_type = []
self.regularizations = []
# self.loss_weight = force_list(loss_weight)
self.loss_weight = tf.Variable(force_list(loss_weight), trainable=False, collections=[tf.GraphKeys.LOCAL_VARIABLES])
self.loss_weight = tf.Variable([float(w) for w in force_list(loss_weight)],
trainable=False, collections=[tf.GraphKeys.LOCAL_VARIABLES])
self.loss_weight_placeholder = tf.placeholder("float")
self.set_loss_weight = tf.assign(self.loss_weight, self.loss_weight_placeholder)
self.target = []

2
rl_coach/architectures/tensorflow_components/heads/policy_head.py
View File

@@ -49,7 +49,7 @@ class PolicyHead(Head):
# a scalar weight that penalizes low entropy values to encourage exploration
if hasattr(agent_parameters.algorithm, 'beta_entropy'):
# we set the beta value as a tf variable so it can be updated later if needed
self.beta = tf.Variable(agent_parameters.algorithm.beta_entropy,
self.beta = tf.Variable(float(agent_parameters.algorithm.beta_entropy),
trainable=False, collections=[tf.GraphKeys.LOCAL_VARIABLES])
self.beta_placeholder = tf.placeholder('float')
self.set_beta = tf.assign(self.beta, self.beta_placeholder)