998c532248615e7ee5fcc974e0b77036764b6a3d,deepchem/rl/tests/test_ppo.py,TestPPO,test_roulette,#TestPPO#,14

Before Change

        env,
        TestPolicy(),
        max_rollout_length=20,
        optimizer=dc.models.tensorgraph.TFWrapper(
            tf.train.AdamOptimizer, learning_rate=0.001))
    ppo.fit(30000)

    // It should have learned that the expected value is very close to zero, and that the best

After Change

        env,
        TestPolicy(),
        max_rollout_length=20,
        optimizer=Adam(learning_rate=0.001))
    ppo.fit(30000)

    // It should have learned that the expected value is very close to zero, and that the best

Instances