6c29a4cfa6530adb71498083a2f5b0504fc83073,tf_agents/agents/ppo/ppo_policy_test.py,PPOPolicyTest,testUpdate,#PPOPolicyTest#,213

Before Change



  def testUpdate(self):
    tf.set_random_seed(1)
    actor_network = tf.make_template("actor_network", _dummy_action_net)
    value_network = tf.make_template("value_network", _dummy_value_net)
    policy = ppo_policy.PPOPolicy(
        self._time_step_spec, self._action_spec, actor_network=actor_network,
        value_network=value_network)
    new_policy = ppo_policy.PPOPolicy(

After Change


  def testUpdate(self):
    tf.set_random_seed(1)
    actor_network = DummyActorNet(self._action_spec)
    value_network = DummyValueNet()

    policy = ppo_policy.PPOPolicy(
        self._time_step_spec,
        self._action_spec,
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 3

Non-data size: 6

Instances


Project Name: tensorflow/agents
Commit Name: 6c29a4cfa6530adb71498083a2f5b0504fc83073
Time: 2018-11-15
Author: oars@google.com
File Name: tf_agents/agents/ppo/ppo_policy_test.py
Class Name: PPOPolicyTest
Method Name: testUpdate


Project Name: tensorflow/agents
Commit Name: 6c29a4cfa6530adb71498083a2f5b0504fc83073
Time: 2018-11-15
Author: oars@google.com
File Name: tf_agents/agents/ppo/ppo_policy_test.py
Class Name: PPOPolicyTest
Method Name: testGaussianDistribution


Project Name: tensorflow/agents
Commit Name: 6c29a4cfa6530adb71498083a2f5b0504fc83073
Time: 2018-11-15
Author: oars@google.com
File Name: tf_agents/agents/ppo/ppo_policy_test.py
Class Name: PPOPolicyTest
Method Name: testUpdate


Project Name: tensorflow/agents
Commit Name: 6c29a4cfa6530adb71498083a2f5b0504fc83073
Time: 2018-11-15
Author: oars@google.com
File Name: tf_agents/agents/ppo/ppo_policy_test.py
Class Name: PPOPolicyTest
Method Name: testDeterministicDistribution