gaspersic/baselines
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

more un-mpying

Browse Source
This commit is contained in:
Peter Zhokhov
2018-11-09 10:08:39 -08:00
parent 84323c3d49
commit 0b8126f949
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
baselines/ppo2/model.py
View File

@@ -124,8 +124,9 @@ class Model(object):
if MPI is None or MPI.COMM_WORLD.Get_rank() == 0: if MPI is None or MPI.COMM_WORLD.Get_rank() == 0:
initialize() initialize()
global_variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope="") else:
sync_from_root(sess, global_variables) #pylint: disable=E1101 global_variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope="")
sync_from_root(sess, global_variables) #pylint: disable=E1101
def train(self, lr, cliprange, obs, returns, masks, actions, values, neglogpacs, states=None): def train(self, lr, cliprange, obs, returns, masks, actions, values, neglogpacs, states=None):
# Here we calculate advantage A(s,a) = R + yV(s') - V(s) # Here we calculate advantage A(s,a) = R + yV(s') - V(s)