gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00
Code Issues Projects Releases Wiki Activity

Release 0.9

Browse Source 
Main changes are detailed below:

New features -
* CARLA 0.7 simulator integration
* Human control of the game play
* Recording of human game play and storing / loading the replay buffer
* Behavioral cloning agent and presets
* Golden tests for several presets
* Selecting between deep / shallow image embedders
* Rendering through pygame (with some boost in performance)

API changes -
* Improved environment wrapper API
* Added an evaluate flag to allow convenient evaluation of existing checkpoints
* Improve frameskip definition in Gym

Bug fixes -
* Fixed loading of checkpoints for agents with more than one network
* Fixed the N Step Q learning agent python3 compatibility
This commit is contained in:
Itai Caspi
2017-12-19 19:27:16 +02:00
committed by GitHub
parent 11faf19649
commit 125c7ee38d
41 changed files with 1713 additions and 260 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
architectures/network_wrapper.py
View File

@@ -75,11 +75,14 @@ class NetworkWrapper(object):
network_is_local=True)
if not self.tp.distributed and self.tp.framework == Frameworks.TensorFlow:
self.model_saver = tf.train.Saver()
variables_to_restore = tf.global_variables()
variables_to_restore = [v for v in variables_to_restore if '/online' in v.name]
self.model_saver = tf.train.Saver(variables_to_restore)
if self.tp.sess and self.tp.checkpoint_restore_dir:
checkpoint = tf.train.latest_checkpoint(self.tp.checkpoint_restore_dir)
screen.log_title("Loading checkpoint: {}".format(checkpoint))
self.model_saver.restore(self.tp.sess, checkpoint)
self.update_target_network()
def sync(self):
"""