e46c1ded997580101e5a5dd3ef0e6501e82f59af,tensorforce/tests/test_tutorial_code.py,TestTutorialCode,test_blogpost_introduction_runner,#TestTutorialCode#,395

Before Change


            target_update_frequency=20,
            states=environment.states,
            actions=environment.actions,
            network=layered_network_builder(network_config)
        )

        agent = DQNAgent(config=agent_config)
        runner = Runner(agent=agent, environment=environment)

        def episode_finished(runner):
            if runner.episode % 100 == 0:

After Change


        from tensorforce.agents import DQNAgent
        from tensorforce.execution import Runner

        environment = MinimalTest(specification=[("int", ())])

        network_config = [
            dict(type="dense", size=32)
        ]
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 3

Non-data size: 4

Instances


Project Name: reinforceio/tensorforce
Commit Name: e46c1ded997580101e5a5dd3ef0e6501e82f59af
Time: 2017-10-16
Author: mi.schaarschmidt@gmail.com
File Name: tensorforce/tests/test_tutorial_code.py
Class Name: TestTutorialCode
Method Name: test_blogpost_introduction_runner


Project Name: reinforceio/tensorforce
Commit Name: bc3343ccf075e2feef0ca832a48ef2cd16335d99
Time: 2017-07-29
Author: mi.schaarschmidt@gmail.com
File Name: tensorforce/core/baselines/mlp.py
Class Name: MLPBaseline
Method Name: create_tf_operations


Project Name: reinforceio/tensorforce
Commit Name: ad1a625cd2b2dd42701435e6174a98c323be5a3e
Time: 2017-10-16
Author: mi.schaarschmidt@gmail.com
File Name: tensorforce/tests/test_reward_estimation.py
Class Name: TestRewardEstimation
Method Name: test_basic