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

Added required arguments to the policy builder in the ACER model to (#784)

Browse Source 
* Added required arguments to the policy builder in the ACER model to
fix the issue #783

* Changed the step model from nbatch to nenvs

* Updated nsteps to be 1.
This commit is contained in:
ethanwaldie
2019-01-22 22:22:28 -05:00
committed by pzhokhov
parent 57e05eb420
commit b55eda1dde
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
baselines/acer/acer.py
View File

@@ -75,8 +75,8 @@ class Model(object):
train_ob_placeholder = tf.placeholder(dtype=ob_space.dtype, shape=(nenvs*(nsteps+1),) + ob_space.shape)
with tf.variable_scope('acer_model', reuse=tf.AUTO_REUSE):
step_model = policy(observ_placeholder=step_ob_placeholder, sess=sess)
train_model = policy(observ_placeholder=train_ob_placeholder, sess=sess)
step_model = policy(nbatch=nenvs, nsteps=1, observ_placeholder=step_ob_placeholder, sess=sess)
train_model = policy(nbatch=nbatch, nsteps=nsteps, observ_placeholder=train_ob_placeholder, sess=sess)
params = find_trainable_variables("acer_model")
@@ -94,7 +94,7 @@ class Model(object):
return v
with tf.variable_scope("acer_model", custom_getter=custom_getter, reuse=True):
polyak_model = policy(observ_placeholder=train_ob_placeholder, sess=sess)
polyak_model = policy(nbatch=nbatch, nsteps=nsteps, observ_placeholder=train_ob_placeholder, sess=sess)
# Notation: (var) = batch variable, (var)s = seqeuence variable, (var)_i = variable index by action at step i