Skip to content

updated policies.py to support tf 2.x #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

updated policies.py to support tf 2.x #7

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions stable_baselines/deepq/policies.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
import tensorflow as tf
import tensorflow.contrib.layers as tf_layers
import tf_slim as tf_layers
import numpy as np
from gym.spaces import Discrete

Expand Down Expand Up @@ -38,7 +38,7 @@ def _setup_init(self):
"""
Set up action probability
"""
with tf.variable_scope("output", reuse=True):
with tf.compat.v1.variable_scope("output", reuse=True):
assert self.q_values is not None
self.policy_proba = tf.nn.softmax(self.q_values)

Expand Down Expand Up @@ -100,13 +100,13 @@ def __init__(self, sess, ob_space, ac_space, n_env, n_steps, n_batch, reuse=Fals
if layers is None:
layers = [64, 64]

with tf.variable_scope("model", reuse=reuse):
with tf.variable_scope("action_value"):
with tf.compat.v1.variable_scope("model", reuse=reuse):
with tf.compat.v1.variable_scope("action_value"):
if feature_extraction == "cnn":
extracted_features = cnn_extractor(self.processed_obs, **kwargs)
action_out = extracted_features
else:
extracted_features = tf.layers.flatten(self.processed_obs)
extracted_features = tf.compat.v1.layers.flatten(self.processed_obs)
action_out = extracted_features
for layer_size in layers:
action_out = tf_layers.fully_connected(action_out, num_outputs=layer_size, activation_fn=None)
Expand All @@ -117,7 +117,7 @@ def __init__(self, sess, ob_space, ac_space, n_env, n_steps, n_batch, reuse=Fals
action_scores = tf_layers.fully_connected(action_out, num_outputs=self.n_actions, activation_fn=None)

if self.dueling:
with tf.variable_scope("state_value"):
with tf.compat.v1.variable_scope("state_value"):
state_out = extracted_features
for layer_size in layers:
state_out = tf_layers.fully_connected(state_out, num_outputs=layer_size, activation_fn=None)
Expand Down